Skip to main content
Glama

codex_subagents

Read-onlyIdempotent

Retrieve and paginate verified subagent events for a Codex task, including child requests, while honoring direct-input availability and offset or cursor refresh rules.

Instructions

Page verified descendants; parent events include child requests. refresh=false uses offset; refresh=true uses cursor. Respect can_accept_direct_input.

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": {
      "task_id": "<task_id>"
    },
    "name": "codex_subagents"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
cursorNoNative cursor
offsetNo
refreshNo
task_idYesTask id
archivedNo

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the bar is lower. The description adds real context beyond them: that parent events are included alongside child requests, and that the pagination mode depends on refresh (offset vs cursor). It stops short of explaining what "verified" means or what happens if a caller mixes offset with refresh=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short fragments, front-loaded and free of padding, which is good. But the fragment style produces an unanchored imperative — "Respect can_accept_direct_input" — with no indication of what that field is or where it appears, so terseness costs clarity here.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the pagination rule is covered. Still, for a 6-parameter read tool the definition leaves key terms ("verified", "can_accept_direct_input") undefined and says nothing about pagination termination or error conditions.

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 coverage is only 33%, so the description carries extra weight; it usefully documents the offset/cursor/refresh interlock that the schema presents as three independent optional fields. However, limit, archived, and task_id receive no description-level explanation, leaving half the parameters dependent on sparse schema text.

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

Purpose3/5

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

"Page verified descendants" gives a verb (page) and a resource (descendants/subagents), so the general operation is discernible. But "verified descendants" is unexplained jargon, and nothing distinguishes this from siblings such as codex_requests, codex_events, or codex_list, which could plausibly return related data.

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

Usage Guidelines2/5

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

The description states how pagination works but never says when to choose this tool over the many sibling listing tools, nor when to pick refresh=true versus refresh=false in practice. An agent must infer the trigger conditions entirely from the parameter coupling rule.

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