Skip to main content
Glama

review_decision

Prepare and record a decision review: inspect claims and revisions, review changed files and provenance, then accept, reaffirm, or retire with a valid token.

Instructions

Prepare a decision review: returns the claim and any operative accepted revision, provenance, the latest inspection and history event (notes shortened), changed files with hunk and line counts and anchor commits since the latest valid inspection for both sets of anchors, and a reviewToken. Request the diff (optionally for specific diffFiles), source previews or full history with include; the token is unchanged. For accepted-guidance inspection use inspectionScope operative on both prepare and inspect; pending proposals remain unassessed. Default all scope covers both revisions. After source inspection, record inspect with inspector, note and token to report no contradiction found without human acceptance. For human review, prepare with all scope, then record accept, reaffirm, or retire with its token, the authorized reviewer, and a reason. Acceptance replaces the operative revision; retirement withdraws the entire record including its proposal. Acceptance requires owner, source, readable Git HEAD, and committed anchor changes. Changed records or code invalidate the token. Identities and approvals are recorded assertions for normal PR review, not authenticated proof.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dir": "<dir>",
      "id": "<id>"
    },
    "name": "review_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesDecision id from get_context or save_decision
dirYesAbsolute path to the project root directory
noteNoReview rationale; required for a verdict. Cite evidence for the decision.
actionNoPrepare is read-only. Inspect records an agent assessment without approval; accept, reaffirm and retire require an authorized review.prepare
includeNoFor prepare only: diff returns the bounded diff since the latest valid inspection, files returns source previews, history returns all review events and the latest two inspections. Omit for a compact preparation.
diffFromNoFor prepare only: lastReview previews changes since the latest inspection still valid for this record and scope (default); capture previews the full history since the evidence baseline.lastReview
reviewerNoIdentity of the actual reviewer; required for a verdict. Never invent one.
diffFilesNoFor prepare with include diff: limit the diff to these changed files.
inspectorNoActual agent or person performing inspection; required for inspect. Does not claim human approval.
reviewTokenNoToken from the prepared review; rejects stale record or code revisions
inspectionScopeNoFor prepare/inspect only: all covers the full record and both anchor sets (default); operative covers only an active accepted revision, leaving a pending draft unassessed. Use the same scope when submitting its token.all

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.24.0
    • addedInput schema / properties / diffFiles
      Added value: +{
      +  "description": "For prepare with include diff: limit the diff to these changed files.",
      +  "items": {
      +    "maxLength": 500,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 20,
      +  "type": "array"
      +}
    • addedInput schema / properties / diffFrom
      Added value: +{
      +  "default": "lastReview",
      +  "description": "For prepare only: lastReview previews changes since the latest inspection still valid for this record and scope (default); capture previews the full history since the evidence baseline.",
      +  "enum": [
      +    "lastReview",
      +    "capture"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / include
      Added value: +{
      +  "description": "For prepare only: diff returns the bounded diff since the latest valid inspection, files returns source previews, history returns all review events and the latest two inspections. Omit for a compact preparation.",
      +  "items": {
      +    "enum": [
      +      "diff",
      +      "files",
      +      "history"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 3,
      +  "type": "array"
      +}
  2. Changed4 schema fields changedv0.22.0
    • changedInput schema / properties / action / description
      Previous value: -"Prepare is read-only. Other actions record an explicitly authorized review."New value: +"Prepare is read-only. Inspect records an agent assessment without approval; accept, reaffirm and retire require an authorized review."
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "prepare",
      -  "accept",
      -  "reaffirm",
      -  "retire"
      -]New value: +[
      +  "prepare",
      +  "inspect",
      +  "accept",
      +  "reaffirm",
      +  "retire"
      +]
    • addedInput schema / properties / inspectionScope
      Added value: +{
      +  "default": "all",
      +  "description": "For prepare/inspect only: all covers the full record and both anchor sets (default); operative covers only an active accepted revision, leaving a pending draft unassessed. Use the same scope when submitting its token.",
      +  "enum": [
      +    "all",
      +    "operative"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / inspector
      Added value: +{
      +  "description": "Actual agent or person performing inspection; required for inspect. Does not claim human approval.",
      +  "maxLength": 200,
      +  "minLength": 1,
      +  "type": "string"
      +}
  3. Addedv0.17.0

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so well. It discloses that acceptance replaces the operative revision, retirement withdraws the entire record, changed records or code invalidate the token, and approvals are recorded assertions rather than authenticated proof. It also states acceptance requires owner, source, readable Git HEAD, and committed anchor changes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and dense with relevant operational details; almost every sentence carries needed context for a complex eleven-parameter, five-action tool. However, it is a single long paragraph with many semicolon-separated rules, which makes it harder to scan than a more structured presentation would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complex lifecycle, no annotations, and no output schema, the description is complete enough to guide correct invocation. It describes the main prepare return payload, token semantics, scope behavior, human versus agent review paths, and important limitations around recorded assertions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all eleven parameters and the baseline is 3. The description adds meaningful workflow semantics beyond the schema, including include/diff behavior, inspectionScope pairing across prepare and inspect, token invalidation, and the roles of inspector, reviewer, note, and token. It does not add much for id, dir, or diffFrom beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the resource and operation: it prepares a decision review and returns the claim, revisions, provenance, inspection/history, changed files, and a reviewToken. It also covers the broader action set via the lifecycle. It is specific but does not explicitly differentiate itself from sibling tools such as save_decision or get_context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit workflow guidance: use prepare first, then inspect for agent assessment, or use accept/reaffirm/retire for human review. It also explains inspectionScope choices, when pending proposals remain unassessed, and the prerequisites for acceptance. This is unusually strong when-to-use guidance for a multi-action tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.