Skip to main content
Glama

codex_requests

Read-onlyIdempotent

Lists pending approval and question summaries in bounded pages with continuation cursors; fetch full request details by id before deciding and never infer approval from silence.

Instructions

Page bounded pending approval/question summaries using cursor. Fetch complete content by id with codex_review_request before approval. Never infer approval from silence or timeout.

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": "codex_requests"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
cursorNoPending-request continuation
task_idNoTask id

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is largely pre-supplied. The description adds real context beyond them: results are bounded summaries requiring a follow-up fetch to see full content, and approval must never be inferred from silence or timeout. It does not mention ordering, page size effects, or what task_id scoping does.

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?

Three short sentences, front-loaded with the core action, followed by the sibling redirect and the safety caveat. No filler, though the second sentence could more explicitly be marked as a prerequisite step rather than a standalone clause.

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?

An output schema exists, so return-value detail is unnecessary, and annotations cover safety. The description covers pagination, truncation risk, and the approval-safety rule, leaving only minor gaps such as ordering or what summary fields are truncated.

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?

With 67% schema coverage, the schema already documents cursor (pending-request continuation) and task_id; the description only reinforces that cursor drives paging. The limit parameter (default 50, max 200) carries no description in either place, and no parameter adds semantics the schema lacks.

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?

States a specific verb and resource: pages through pending approval/question summaries using a cursor, and contrasts itself with codex_review_request for full content. It is clearly distinguishable from the sibling it names, though it never explicitly says the list is read-only or what a summary contains.

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?

Gives a concrete workflow rule: fetch complete content by id with codex_review_request before approval, which tells the agent when to leave this tool. It does not state exclusions (e.g., when not to page at all, or what to do when the list is empty) beyond the silence/timeout warning.

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