Skip to main content
Glama

review

Evaluate a run's branch and plan, or uncommitted changes when no run_id is given, returning approve or changes_requested to guide code acceptance.

Instructions

Review a run's branch (with its plan), or uncommitted changes when run_id is omitted. Starts with VERDICT: approve | changes_requested.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "review"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoRepository path
agentNo
focusNo
modelNo
effortNo
run_idNo
sessionNoRun group labeldefault
context_runsNoFinished run ids to pass in as context

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.3

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose the output contract: the response starts with VERDICT: approve | changes_requested. However, it omits other important traits: the agent, model, and effort parameters imply it spawns an LLM review, yet the description does not state cost, latency, or whether the operation is read-only.

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

Conciseness5/5

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

Two sentences, both necessary, with the two modes and the omitted-run_id fallback front-loaded. No filler and no restatement of the tool name.

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

Completeness3/5

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

For an 8-parameter tool with no annotations and no output schema, the description covers the mode switch and hints at the return format, which is genuinely useful. It still leaves the reviewer-configuration parameters and the operational characteristics of an agent-backed review unexplained, so it is only minimally adequate.

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?

Schema coverage is 38% across 8 parameters, so the description must compensate, and it gives meaningful semantics for only run_id by explaining that omitting it switches to uncommitted changes. The remaining parameters, including focus, agent, model, effort, context_runs, and session, get no explanation of what they control.

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 states a specific verb and two concrete resources: a run's branch including its plan, or uncommitted changes. The run_id-omitted conditional clearly separates the two operating modes, which makes it distinguishable from siblings like merge or discard, though the bare verb 'review' leaves the domain (code review) to inference.

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

Usage Guidelines4/5

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

It explicitly tells the agent which mode is selected by presence or absence of run_id, which is the main routing decision. It gives no when-not-to-use guidance and never points to siblings such as explain, status, or merge, so alternatives remain unaddressed.

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