Skip to main content
Glama

record_review

Records a reviewer’s pull request verdict for a ticket—commit reviewed, pass/change/block result, verification evidence, findings, and resolved status—so review decisions stay auditable.

Instructions

Record your review of a ticket's pull request, the same verdict you post to GitHub: head the commit you reviewed, verdict pass, changes or block, verified what you ran and what it showed, not_verified what you did not cover and why, findings [{"severity": "P1|P2|P3", "file": "", "line": 0, "blocking": true, "text": ""}], and on a re-review resolved marking each earlier finding {"F1": "fixed", "F2": "open"}. A pass leaves no blocking finding open. Only the reviewer records reviews.

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": {
      "ticket": "<ticket>",
      "head": "<head>",
      "verdict": "<verdict>",
      "verified": "<verified>"
    },
    "name": "record_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
headYes
ticketYes
projectNo
verdictYes
findingsNo
resolvedNo
verifiedYes
not_verifiedNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations exist, so the description carries full disclosure burden. It contributes real behavioral rules: the pass/blocking-finding invariant, the reviewer-only restriction, and re-review semantics via `resolved`. It does not say whether this posts to GitHub, whether it overwrites a prior review, whether it is idempotent, or what happens on failure, which matters for an unannotated mutation.

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?

Front-loaded with the core action, then the field glossary in the order an agent would fill them. Dense but every clause carries payload semantics or a rule. The inline JSON snippets are compact and functional rather than filler.

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

Completeness4/5

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

For an eight-parameter mutation with zero annotation and zero schema-description coverage, the description does most of the necessary work, and the output schema covers return values. The one residual ambiguity is whether recording here is the same act as posting to GitHub or merely mirrors it, which affects whether the agent should also call something else.

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 0% and the schema only supplies bare titles, so the description must compensate, and it largely does: it defines head, verdict values (pass, changes, block), what verified vs not_verified should contain, the exact findings object shape with severity enum P1|P2|P3, and the resolved map format {"F1": "fixed"}. Only `ticket` and `project` are left unexplained, which are the most self-evident of the eight.

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?

Names a specific verb and resource: recording a review of a ticket's pull request, mirroring the verdict posted to GitHub. It even enumerates the payload concepts (head, verdict, verified, not_verified, findings, resolved), so the agent knows exactly what kind of record this creates. It stops short of naming a sibling such as record_finding, so differentiation is inferred from the payload rather than stated.

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

Usage Guidelines3/5

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

Usage is only implied: you call it when you have reviewed a PR, and on a re-review you supply `resolved`. The role constraint 'Only the reviewer records reviews' is a useful gate, and 'A pass leaves no blocking finding open' constrains when a pass verdict is legal. But there is no explicit when-not guidance and no routing to record_finding for standalone findings.

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