Skip to main content
Glama
AmirShayegh

codex-claude-bridge

by AmirShayegh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

review_plan

Review an implementation plan before writing code to catch issues early. Returns an approve/revise/reject verdict and findings, with a session_id to carry context into the code review.

Instructions

Get an independent code review of your implementation plan before writing code. Call this after drafting a plan and before implementing it. Returns a verdict (approve/revise/reject), findings, session_id, responding models, and persistence provenance. Pass the returned session_id to review_code later so the reviewer has full context.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoAbsolute path to the directory this review runs in — the repository or git worktree whose code is being reviewed. Auto-capture, repository instruction files, and the reviewer subprocess all use it. Always pass it: an auto-capturing review without it is refused unless the server is configured with "require_cwd": false, in which case the server's launch directory is used. Must be absolute; "~" is not expanded. Applies to this call only — pass it again on resume.
planYesThe implementation plan to review
depthNoReview depth
focusNoReview focus areas
modelNoOverride the configured default model for this call (e.g., "gpt-5.6-sol"), or "latest". Or pick a tier instead of a model id: "max" (hardest problems — architecture, concurrency, security, subtle bugs), "balanced" (everyday review), or "fast" (small diffs, precommit sanity, quick iteration). Tiers map per provider (Codex: gpt-6-astra / gpt-5.6-sol / gpt-5.6-luna; Gemini: 3.1 Pro (High) / 3.8 Flash (High) / 3.8 Flash (Medium)) and survive failover. May be combined with session_id to change model mid-session; without it a resumed session keeps the model it was recorded with. Compare returned resolved and observed labels for runtime changes.
contextNoProject context and constraints
deliberateNoPer-call override of the configured review mode: true = both providers review (deliberation); false = single provider with failover. Omit to use the configured mode. Requires a two-provider setup; requesting deliberation under a single-provider config returns an error. Under deliberate-deep, the returned verdict reflects both providers' independent reviews and is NOT recomputed from cross-review adjudications — treat deliberation.divergent[].adjudication as advisory input for your own synthesis.
session_idNoContinue from a previous review session

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral disclosure burden. It discloses the return payload (verdict with approve/revise/reject, findings, session_id, responding models, persistence provenance) and the session continuation contract. It does not enumerate failure modes or side effects, but for a read-only review tool this is reasonably complete.

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?

The description is two sentences with zero filler: the first front-loads purpose and timing, the second states the return value and the session chaining behavior. Every clause carries new information, and the sibling reference is integrated without unnecessary detail.

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?

Since there is no output schema, the description compensates by listing the return fields and the session flow. Eight parameters exist, but each is thoroughly documented in the schema, leaving the description to cover the when/why/what-returns glue. It could briefly mention depth/focus, but the schema already provides their semantics.

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 the baseline is 3 even though the main description says little about individual parameters. The description's reference to session_id adds cross-call context beyond the schema's per-field text, but it does not need to compensate for uncovered parameters. It neither improves nor harms the schema's already rich parameter semantics.

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 states a specific verb and resource: 'Get an independent code review of your implementation plan before writing code.' It also names the handoff to sibling review_code, making the distinction from the sibling code-review tools explicit. An agent can immediately tell this tool is for plans, not code.

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

Usage Guidelines5/5

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

The description explicitly says when to call it ('after drafting a plan and before implementing it') and how it sequence with an alternative sibling: 'Pass the returned session_id to review_code later so the reviewer has full context.' This gives the agent both timing and routing guidance with no inference required.

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

Deploy Server

Other Tools