Skip to main content
Glama

codex_send

Destructive

Send a follow-up turn to an active Codex task or steer ongoing work using the expected turn ID; follow-ups can choose a supported model and effort.

Instructions

Send a follow-up turn or steer active work. Steering needs the current expected_turn_id; follow-ups can select a supported model/effort.

Input Schema

NameRequiredDescriptionDefault
modeNofollow_up
modelNo
effortNo
imagesNo
promptYes
skillsNo
task_idYesTask id
request_idNoKey for identical retries
operation_idNoAlias of request_id
context_filesNo
output_schemaNo
expected_turn_idNo

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is known; the description's added value is the expected_turn_id precondition for steering. It does not disclose what a steer does to in-flight work (cancel? interrupt?) or that the same request_id replays safely despite idempotentHint=false, which matters for a destructive send.

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 dense sentences with the mode distinction front-loaded and no filler. Slightly terse to the point of ambiguity — 'supported model/effort' leaves the agent unsure where the valid set is defined.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

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

For a 12-parameter destructive mutation with nested objects and an output schema present, the description covers only the two mode names and one precondition. It omits mode-specific parameter applicability (which fields are meaningful for steer vs follow_up) and any side-effect framing, leaving significant gaps an agent must guess at.

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

Parameters2/5

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

Schema description coverage is only 25% across 12 parameters, and the description explains just three of them (expected_turn_id, model, effort). High-impact inputs such as images, skills, context_files, output_schema, and the request_id/operation_id aliasing receive no added meaning, so the description does not compensate for the sparse 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?

States a concrete action (send a turn) and names its two modes, follow_up and steer, with what each does. An agent can grasp what the tool does, but the description never distinguishes it from likely-overlapping siblings such as codex_respond or codex_queue.

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?

Gives one real precondition — steering requires the current expected_turn_id — which is actionable guidance. However, it never says when to steer versus follow up, when to use this instead of codex_respond/codex_interrupt, or what happens on a task already busy, so the agent must infer mode selection from the enum alone.

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