Skip to main content
Glama

Review workspace changes with Codex

codex_review

Inspect uncommitted changes in a workspace. Provides severity-ordered findings and a sessionId to continue the review.

Instructions

Ask Codex to review the uncommitted changes in a workspace (read-only sandbox, no files modified). Returns findings ordered by severity plus a sessionId usable with codex_continue.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYesAbsolute path of the workspace to review
focusNoOptional focus for the review, e.g. "security of the auth module"
modelNoCodex model override
terminalNoOpen a Terminal window streaming live progress (default: env CODEX_MCP_TERMINAL=1)
timeoutMsNoMax execution time per attempt in ms; auto-resume may add attempts (default: 60 minutes)
writeNotesNoPersist a markdown summary of this run to <cwd>/.codex-flow/notes/<sessionId>.md (default false).
baselineRefNoOptional git ref to review from: Codex reviews `git diff <baselineRef>..HEAD` plus current uncommitted changes, so checkpoint/merge commits made since the baseline are covered.
reasoningEffortNoReasoning effort override for the selected model

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
diffYes
runIdYes
usageYes
errorsYes
statusYes
stderrYes
abortedYes
liveLogYes
attemptsNo
commandsYes
exitCodeYes
timedOutYes
warningsYes
notesPathYes
sessionIdYes
turnCountYes
attributionYes
fileChangesYes
parseErrorsYes
agentMessageYes
resumeReasonsNo
sawCompletionYes
schemaVersionYes
unknownEventsYes
outputTruncatedYes
Behavior4/5

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

With no annotations, the description carries full burden. It discloses the read-only nature and output structure (findings ordered by severity + sessionId). It does not cover rate limits or auth needs, but for a read-only review tool this is sufficient.

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, front-loaded with purpose and safety, followed by output details. No wasted words. Every sentence adds value.

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?

With an output schema and full parameter descriptions, the description covers purpose, safety, and output. It could mention prerequisites (e.g., git repository) but is complete enough for a review tool.

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 100%, so baseline is 3. The description does not add significant meaning beyond the schema. It reinforces 'uncommitted changes' but does not elaborate on parameters like baselineRef or focus.

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

Purpose5/5

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

The description clearly states the verb 'review' and the resource 'uncommitted changes in a workspace', and adds the qualifying note 'read-only sandbox, no files modified'. This distinguishes it from sibling tools like codex_execute and codex_metrics.

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?

The description implies usage when reviewing uncommitted changes and mentions a sessionId usable with codex_continue. However, it lacks explicit when/ when-not guidance or alternatives among siblings.

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/anhnguyen0905/codex-mcp'

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