Skip to main content
Glama

write_review

Record review decisions for artefacts (tasks, reports, code changes) using structured review files. Supports approval, rejection, requests for changes, or escalation to human review.

Instructions

Write a REVIEW file (governance-layer decision, per ADR-0017/0025).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reviewer_roleYesRole code of the reviewer (must have ``review_decision`` capability; typically ``layer: governance`` or ``layer: admin``).
subject_typeYesWhat is being reviewed. One of ``task`` / ``report`` / ``role_switch`` / ``code_change``.
subject_refYesReference to the artefact under review — file path for task/report/code_change; fcop.json diff range for role_switch.
decisionYesReview decision. One of: ``approved`` — artefact is accepted; ``rejected`` — artefact is rejected (cannot proceed); ``needs_changes`` — must be revised (requires ``required_changes``); ``abstained`` — reviewer recuses; ``needs_human`` — reviewer escalates to human (ADR-0025, v1.1). The review stays pending until ``mark_human_approved`` is called to close the loop.
rationaleNoFree-text rationale for the decision. Recommended for all non-``approved`` decisions.
required_changesNoNewline- or comma-separated list of required changes. Mandatory when ``decision=needs_changes``.
reviewer_agentNoOptional agent/session identifier on top of the role code.
bodyNoAdditional Markdown body after the frontmatter.
subject_shortNoOverride the ``-on-{slug}`` segment of the filename. Auto-derived from ``subject_ref`` when omitted.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior1/5

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. The description only states it writes a REVIEW file, with no information about side effects, permissions, idempotency, or whether it's destructive. This is a significant gap for a mutation tool.

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 a single concise sentence that communicates the core action. It is appropriately front-loaded but could benefit from a bit more context without becoming verbose.

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

Completeness2/5

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

Despite having an output schema, the description lacks details about what the REVIEW file contains, how it affects the artefact under review, and the overall workflow. For a tool with 9 parameters in a governance context, this is insufficient.

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

Parameters3/5

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

The input schema has 100% coverage with detailed descriptions for all 9 parameters. The tool description adds no additional meaning beyond what the schema already provides, so baseline score of 3 applies.

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 tool writes a REVIEW file for governance-layer decisions, referencing ADR-0017/0025. This distinguishes it from sibling tools like read_review and list_reviews. However, it could be more explicit about creating a new review record.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives. The description mentions ADRs but does not provide context on prerequisites, when-not-to-use, or comparisons to sibling tools like approve_task or mark_human_approved.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/joinwell52-AI/FCoP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server