Skip to main content
Glama

codex_queue

Destructive

Manage a queue of Codex coding tasks: add, list, update, delete, reorder, or start prompts with optional images, context files, and skills.

Instructions

list takes cursor/limit; add takes prompt and optional images/context_files/skills; update also needs queued_id; delete needs queued_id; reorder needs ordered_ids; start takes optional queued_id. Mutations need an operation key.

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_queue"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
actionNolist
cursorNoNative cursor
imagesNo
promptNo
skillsNo
task_idYesTask id
queued_idNo
request_idNoKey for identical retries
ordered_idsNo
operation_idNoAlias of request_id
context_filesNo

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 destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The one genuinely additive sentence is 'Mutations need an operation key', which explains the retry/idempotency key expected of mutating actions — useful context not present in the annotations. It stops short of saying what delete or reorder destroy, or what `start` does to a queued item, so it is helpful but thin.

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?

Dense and front-loaded with no filler; every clause carries a parameter requirement. The semicolon-run format is scannable enough, though the 'also needs' phrasing in the update clause introduces avoidable ambiguity.

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. But for a destructive, six-action, twelve-parameter tool, the description omits the overall purpose of the queue and the consequences of the mutating actions, leaving only the parameter dependency map as its contribution.

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 33% across 12 flat parameters with a single required field, so the description must carry the conditional-dependency burden — and it does, mapping all six action values to their required and optional inputs. The compensation is incomplete: 'update also needs queued_id' is ambiguous about whether a prompt is also required, and per-action applicability of limit/cursor is only implied.

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

Purpose2/5

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

The description never states what the tool operates on or what it is for — it only enumerates which parameters each `action` value requires. An agent can infer that a six-way 'queue' verb set exists, but not whether the queue holds prompts, tasks, or messages, and nothing distinguishes it from siblings such as codex_list or codex_start.

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 action-to-parameter mapping implicitly tells the caller which fields to supply for each mode, which is a form of usage guidance. However, there is no statement of when to choose `start` versus `add`, no prerequisites, and no mention of the siblings an agent should prefer for listing or starting work.

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