Draft Evaluation Terms of Reference
Write terms of reference for commissioning an external evaluation, including scope, questions, and methodology.
Draft: Draft Evaluation Terms of Reference
Your Prompt
- What You Need
- Supply the commissioning purpose, decisions, program documents, scope, timing, available data, budget or procurement rules, and any binding evaluation standard.
- Choose This Prompt When
- Use this before hiring or commissioning an evaluation; choose evaluation design review when a design already exists.
Describe your goal, audience, available information and constraints. Your words are added to the prompt as supplied. You can also use the guided fields below.
Kept in this tab while you work. Copy and Start includes this description.
Copy this prompt and paste it into your AI chat to start. If it needs source material, the AI will ask for it.
Evidence and applicability: use only supplied or verifiable evidence for historical facts, values, quotations, completed activities and approvals. Preserve conflicting sources with their provenance; do not choose a preferred value without adjudication. Mark missing evidence as unknown or not evidenced, not as proof an activity never occurred. Keep proposed plans and illustrative examples separate from findings. Never invent a baseline, quote, pilot, validation or sign-off to complete a template. Match methods to the purpose and population; a suitable single-method design is valid. Distinguish descriptive change from causal attribution. Check obligations in the applicable funding agreement rather than assuming a universal donor rule.
Use only program material supplied in this chat. Ask me to paste evaluation purpose, users and decisions, program design, commissioning constraints, and any applicable requirements if essential details are absent. Do not treat this request as evidence that those materials exist.
Draft terms of reference for an evaluation that a prospective evaluator could scope and price. If the evaluation purpose, subject, or intended users are missing, ask for them before presenting a commissionable TOR. Treat dates, budget, deliverables, approvals, and standards not supplied as proposed or to be confirmed.
Include program and evidence background; purpose, intended users, and decisions; boundaries of population, geography and period; a small set of prioritized, answerable evaluation questions; criteria selected for this purpose rather than automatically using every OECD DAC criterion; suggested design options and minimum methodological expectations; data access, sampling, analysis, ethics, inclusion, and limitations; stakeholder participation; deliverables, review process, roles, and schedule; and any budget or procurement constraints actually supplied. Let bidders justify feasible methods rather than prescribing a mixed-method package by default. Separate what the commissioner has decided from options for decision. Identify missing information that affects feasibility or price.
State quality assurance and ethics responsibilities, how the draft report will be reviewed, and who will resolve conflicting comments, if those roles are known.
Check: Score It with the Evaluation ToR Quality Rubric
The Review Prompt
Paste the draft at the bottom of this prompt and run it. It scores each criterion from 1 to 5 and says why.
Establish the document purpose, design, stage, applicable requirements, and available source evidence before rating. Distinguish N/A with a reason, not evidenced, unresolved conflicting evidence, and observed inadequate performance. Missing records do not prove an activity did not occur. Missing records alone justify evidence requests and a deferred readiness decision, not an inferred failure or mandatory repeat activity. Do not invent documentary, signature or approval requirements. Cite document locations for every finding. Keep supported facts separate from proposals, assumptions, and illustrative examples. Never invent completed fieldwork, validation, consent, approval, values, dates, quotations, or assigned ownership. Label unconfirmed owners and proposed revisions for confirmation. Report blocking ethics, safety, confidentiality, measurement-validity, or inference failures first regardless of scores. Give a total and band only when all five dimensions are applicable and sufficiently evidenced with no unresolved evidence conflict; otherwise show the dimension profile, coverage, and evidence requests without a total, band, or rescaled equivalent. A documentation score never authorizes use, fielding, compliance, or approval.
You are an expert M&E evaluation specialist. Score the evaluation Terms of Reference (ToR) I will provide using the rubric below.
SCORING RUBRIC - Evaluation ToR Quality Rate each applicable, evidenced dimension 1-5. Choose the highest anchor fully supported by the evidence; a material defect takes precedence over a favorable element count. An absent required feature in a complete submitted artifact is an observed documentation defect; an unavailable source or record is not evidenced, not proof the underlying activity failed.
DIMENSION 1: Background and Scope Clarity
- Score 5: All four elements present and well-developed. Program described specifically (what, where, when, target population, scale), evaluation purpose explicit (formative, summative, or mixed; at what decision point), intended users named (named roles or organizations), decision context articulated (what decisions will be informed by findings).
- Score 4: Three of four elements adequately specified; the remaining element incomplete: May lack named decision context or fully named users.
- Score 3: Two of four elements adequately specified; the others incomplete. Program description and purpose stated, but users or decision context generic.
- Score 2: One element present. Background reads as boilerplate without specific scope or users.
- Score 1: No clear background or scope. ToR jumps straight to tasks without context.
DIMENSION 2: Evaluation Questions and Criteria
- Score 5: All 4 elements: Evaluation questions are specific and answerable with the proposed methods, each question is mapped to one or more evaluation criteria (relevance, coherence, effectiveness, efficiency, impact, sustainability, or alternatives), sub-questions identified where needed for answerability, and the user or decision-maker for each question is named.
- Score 4: Three of four elements adequately specified; the remaining element incomplete: Questions are answerable and mapped to criteria; sub-questions or named users partially present.
- Score 3: Two of four elements adequately specified; the others incomplete. Questions present but criteria mapping is implicit. No sub-questions or named users.
- Score 2: Questions are vague ("How successful was the program?") or unanswerable with the proposed methods. No criteria mapping. No sub-questions.
- Score 1: No evaluation questions, OR questions are tasks rather than questions ("Conduct an evaluation of...").
DIMENSION 3: Methodology Specification
- Score 5: All 4 elements: Design type named (e.g., quasi-experimental, mixed-methods case study, contribution analysis) with rationale tied to evaluation questions, sampling expectations specified (probability or purposive, approximate size or range), primary and secondary data sources listed, analysis approach described (e.g., mixed-methods integration plan, qualitative coding, statistical methods).
- Score 4: Three of four elements adequately specified; the remaining element incomplete: Design and approach named; sampling or analysis briefly described.
- Score 3: Two of four elements adequately specified; the others incomplete. Design type named but rationale generic. Sampling or analysis vague.
- Score 2: Methodology described as "mixed methods" or similar without specification. No design rationale.
- Score 1: No methodology specified, OR ToR specifies methods that cannot answer the evaluation questions.
DIMENSION 4: Deliverables, Timeline, and Budget Realism
- Score 5: All five elements present. Deliverables listed with content specifications (e.g., inception report, draft report, final report, presentation), milestones tied to specific dates or weeks, total days and cost or budget envelope stated, payment schedule linked to deliverables, communication plan with frequency and format.
- Score 4: Four of five elements adequately specified; the remaining element incomplete. Deliverables and milestones clear; budget or payment schedule may be partial.
- Score 3: Three of five elements adequately specified; the others incomplete. Deliverables and timeline present but budget or payment schedule absent. No communication plan.
- Score 2: Two or fewer elements present. Deliverables listed but with no milestones, budget, or schedule.
- Score 1: No specified deliverables, timeline, or budget. ToR is unreasonable to bid on.
DIMENSION 5: Ethics and Stakeholder Engagement Plan
- Score 5: All 4 elements: Consent and safeguarding requirements specified for all data subjects, vulnerable population protections defined (children, conflict-affected, marginalized groups), stakeholder validation plan included (when findings will be reviewed by program staff, beneficiaries, or partners), dissemination plan addresses post-evaluation communication.
- Score 4: Three of four elements adequately specified; the remaining element incomplete: Consent and validation present; vulnerable population protections or dissemination plan partial.
- Score 3: Two of four elements adequately specified; the others incomplete. Consent referenced and one other element present. No detailed safeguarding or validation.
- Score 2: Ethics referenced as a checkbox ("evaluators will follow ethical standards") without specification. No validation or dissemination plan.
- Score 1: No ethics or stakeholder engagement provisions.
OUTPUT FORMAT: Return your assessment as a table followed by a summary:
| Dimension | Score (1-5), N/A, or Not Evidenced | Evidence from ToR | Priority Revision |
|---|---|---|---|
| Background and Scope Clarity | |||
| Evaluation Questions and Criteria | |||
| Methodology Specification | |||
| Deliverables, Timeline, and Budget Realism | |||
| Ethics and Stakeholder Engagement Plan |
First report blocking issues, unresolved conflicts, applicability and evidence coverage. Only if all five dimensions are applicable and sufficiently evidenced with no unresolved source conflict, report Total: X/25 and Band: Strong (22-25) / Adequate (17-21) / Needs Revision (11-16) / Substantial Revision (5-10), as a secondary documentation summary. Otherwise omit both total and band; report the dimension profile and evidence requests without rescaling. Single Most Important Revision: [One specific sentence] Procurement Risk: [None / Minor clarifications needed / Recommend revision before issuing / Do not issue without major revision]
For any dimension scored 1 or 2, add a brief explanation and a concrete revision example.
EVALUATION ToR TO SCORE: [Paste your evaluation Terms of Reference here]
Fix: Revise What Scored Low
The Revise Prompt
Paste the draft and its scores at the bottom of this prompt. It revises the parts that scored below 4.
Establish the document purpose, design, stage, applicable requirements, and available source evidence before rating. Distinguish N/A with a reason, not evidenced, unresolved conflicting evidence, and observed inadequate performance. Missing records do not prove an activity did not occur. Missing records alone justify evidence requests and a deferred readiness decision, not an inferred failure or mandatory repeat activity. Do not invent documentary, signature or approval requirements. Cite document locations for every finding. Keep supported facts separate from proposals, assumptions, and illustrative examples. Never invent completed fieldwork, validation, consent, approval, values, dates, quotations, or assigned ownership. Label unconfirmed owners and proposed revisions for confirmation. Report blocking ethics, safety, confidentiality, measurement-validity, or inference failures first regardless of scores. Give a total and band only when all five dimensions are applicable and sufficiently evidenced with no unresolved evidence conflict; otherwise show the dimension profile, coverage, and evidence requests without a total, band, or rescaled equivalent. A documentation score never authorizes use, fielding, compliance, or approval.
You are an expert M&E evaluation specialist. Review the draft evaluation ToR I will provide and fix every problem that falls below the Good (4) threshold on the Evaluation ToR Quality rubric.
Separate supported corrections from evidence requests and proposed text requiring confirmation. A plausible owner, date, rationale, or account of an activity is not a verified fact. Preserve unresolved source conflicts.
WHAT TO LOOK FOR AND FIX:
Background problems: Generic program description without specifics. Evaluation purpose unstated or boilerplate ("to assess effectiveness"). Users unnamed or stated as "the donor" without specificity. No decision context.
Evaluation Questions problems: Questions that are tasks not questions ("Conduct an analysis of..."). Vague or unanswerable questions. No mapping to evaluation criteria. Sub-questions missing where needed for answerability. Intended users or decisions unclear.
Methodology problems: "Mixed methods" without specifying which methods. Sampling left to the evaluator without parameters. Analysis approach unstated. Design type without rationale.
Deliverables and Budget problems: Deliverables listed without content specifications. Milestones without dates. Budget envelope or daily rate ranges absent. Payment schedule not linked to deliverables. No communication plan.
Ethics problems: Ethics referenced as a checkbox. Vulnerable population protections absent. No validation plan with stakeholders. No dissemination plan.
OUTPUT FORMAT: For each problem found:
- Dimension: [which dimension]
- Location: [which section of the ToR]
- Problem: [one sentence describing what is wrong]
- Revised version: [the corrected text]
Then provide the complete revised ToR incorporating all corrections.
DRAFT ToR TO REVISE: [Paste your draft Terms of Reference here]