Skip to main content
Glama

codex_review

Destructive

Run native code reviews on uncommitted changes, base branches, commits, or custom instructions, then poll for findings and results.

Instructions

Start native code review of uncommitted changes, a base branch, a commit or custom instructions on an idle task. Poll for findings/results.

Input Schema

NameRequiredDescriptionDefault
branchNo
commitNo
targetNouncommittedChanges
task_idYesTask id
request_idNoKey for identical retries
instructionsNo
operation_idNoAlias of request_id

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, readOnlyHint=false and non-idempotent, which is a serious profile the description does not elaborate on. The description adds two pieces of behavior beyond the annotations — that the task must be idle and that results are obtained by polling — which is real value, but it never explains what state gets destroyed, whether a review can be cancelled, or how long polling takes.

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?

Two short sentences, front-loaded with the action and followed by the result-retrieval behavior. Nothing is wasted, though the second sentence ('Poll for findings/results') is terse enough to be ambiguous about whether this tool itself blocks.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile for what is a destructive, open-world mutation. Still missing for a 7-parameter mutation tool: the idle-task precondition's failure mode, guidance on combining branch/commit with target, and retry/idempotency behavior.

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 description coverage is only 43%, so the description carries some burden. It does clarify what the target values mean (uncommitted changes, base branch, commit, custom instructions), which compensates for the undocumented enum. However, it says nothing about the request_id/operation_id retry-alias mechanism or the anyOf requirement, leaving idempotency semantics entirely to 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 names a specific verb and resource ('Start native code review') and enumerates the four review targets (uncommitted changes, base branch, commit, custom instructions), which maps directly onto the target enum. It does not explicitly differentiate itself from the sibling codex_review_request, so an agent must infer the split, but the purpose itself is unambiguous.

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?

The phrase 'on an idle task' is the only usage condition offered, and it usefully signals a precondition. There is no explicit when-to-use versus codex_review_request, codex_diff, or codex_review alternatives, and no statement about what an agent should do if the task is not idle.

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