Skip to main content
Glama

codex_capabilities

Read-onlyIdempotent

Check a task’s native collaboration and permission options plus direct-input capability to determine how Codex can interact with that task.

Instructions

Discover native collaboration/permission options and direct-input capability for a task.

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_capabilities"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYesTask id

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

C2.6/5.0
Behavior2/5

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 fully covered by structured data. The description adds no behavioral context beyond that: it does not explain what 'native' means, whether results vary over the task lifecycle, or how discovered options constrain subsequent tool calls, which matters for an open-world discovery tool.

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?

A single clause with no wasted padding, and the capability-discovery intent is front-loaded. It is slightly compressed to the point of ambiguity ('native collaboration/permission options'), but nothing is redundant.

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?

An output schema exists, so return values need not be described, but the tool is open-world and its results presumably gate later actions, and the description never explains that relationship or when to re-check capabilities. For a discovery tool that other calls may depend on, this leaves a real gap in decision-relevant context.

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?

Only one parameter exists and schema coverage is 100%, with task_id documented in the schema itself. The description's 'for a task' confirms the parameter's role but adds no format, sourcing, or validity detail beyond the schema's min/max length constraints, so the baseline of 3 applies.

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?

The verb 'Discover' plus the object 'collaboration/permission options and direct-input capability' gives a rough idea of a read-only capability probe scoped to a task, but the phrasing is abstract jargon. An agent cannot tell from this sentence what concrete output to expect (a list of permissions? a boolean for direct input?) or how it differs from siblings like codex_status, codex_settings, or codex_skills, which sound related.

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?

There is no statement of when this tool should be invoked, no prerequisites, and no alternative named. The phrase 'for a task' implies it is scoped per task, but not whether it should be called before delegating, before sending direct input, or on error. Usage is left entirely to inference from the name.

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