Skip to main content
Glama

Answer Codex

codex_respond

Answer Codex approval or question requests so blocked work can continue. Provide a decision or question answers, and ask the user first for risky or architectural choices.

Instructions

Answer a request Codex is blocked on (listed in pending_requests). Approvals take decision: accept | acceptForSession | decline | cancel. Questions take answers: { : "answer" }. Ask the user first for risky/destructive actions or architectural choices.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "request_id": "<request_id>"
    },
    "name": "codex_respond"
  }
}

Input Schema

NameRequiredDescriptionDefault
answersNo
decisionNo
request_idYes
wait_secondsNoSeconds to block before returning a progress snapshot (default 120). Returns early when the turn finishes or Codex needs an answer. The turn keeps running after this returns.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.3/5.0
Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden. It discloses the approval vocabulary and the safety norm of asking the user first, but says nothing about what happens after submission (whether the turn resumes, whether acceptForSession persists for the session, what a stale request_id yields) or the consequences of each decision value. Useful context, but meaningful gaps for a tool that can authorize destructive operations.

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?

Three tight sentences, front-loaded with the core action, then the per-mode mechanics, then the safety rule. 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.

Completeness5/5

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

Given four parameters, a nested answers object, and no output schema or annotations, the definition covers what an agent needs: which requests are eligible, the payload shape for each mode, and the escalation rule. Return behavior is partially covered by the wait_seconds schema description, so the description itself need not repeat it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (just wait_seconds), so the description must compensate — and it largely does, explaining that approvals use decision with its four values and that questions use answers keyed by question id with a string/array payload. request_id is only implied by the pending_requests reference rather than explicitly defined, which keeps it off a 5.

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?

States a concrete verb and resource: answering a request that Codex is blocked on, and points at where those requests appear (pending_requests). It also splits the tool's two modes (approvals vs questions), which distinguishes it from siblings like codex_wait or codex_steer that observe or redirect rather than unblock.

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 clear triggering context (requests listed in pending_requests) and a strong conditional rule: consult the user first for risky/destructive actions or architectural choices. It stops short of explicit exclusions — e.g. when to prefer codex_interrupt or codex_steer instead of answering — but the when-to-use guidance is unambiguous.

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