Skip to main content
Glama

codex_plans

Destructive

Manage bounded dependency plans by submitting, inspecting, listing, or canceling through ordinary task admission; unknown outcomes wait for explicit resume without retrying side effects.

Instructions

submit: spec/key; inspect: plan_id; list: offset/limit; cancel: plan_id/key. Runs bounded dependency plans through ordinary task admission. Unknown outcomes wait for explicit resume; no side effect is retried.

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": {
      "action": "<action>"
    },
    "name": "codex_plans"
  }
}

Input Schema

NameRequiredDescriptionDefault
specNoVersion 1 dependency plan; see the tools documentation.
limitNo
actionYes
offsetNo
plan_idNo
request_idNoKey for identical retries
operation_idNoAlias of request_id

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructive=true, idempotent=false and openWorld=true, but the description adds genuinely new behavioral facts: unknown outcomes block until an explicit resume, and no side effect is retried. The no-retry guarantee is especially valuable given idempotentHint=false, since it tells the agent not to expect safe replay. It does not describe what gets destroyed or any permission requirements, which keeps it below 5.

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 sentences, front-loaded with the action/parameter matrix so the agent sees dispatch rules first and semantics second. There is no filler. The compressed shorthand ('spec/key', 'offset/limit') is slightly cryptic and costs a little readability, so not a 5.

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 action matrix covers dispatch. But for a destructive, open-world tool with seven parameters and a nested spec object, the description gives no sense of plan structure beyond pointing at external documentation, and failure/interrupt behavior is covered by a single clause.

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 43%, but the description compensates by binding each action to its parameters: submit takes spec/key, inspect takes plan_id, list takes offset/limit, cancel takes plan_id/key. This explains the required-parameter asymmetry of the action enum, which the schema alone does not. The operation_id alias parameter is left undisclosed in the description.

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?

The description states a concrete verb and resource: it 'runs bounded dependency plans through ordinary task admission,' and the leading clause enumerates the four actions (submit/inspect/list/cancel). An agent can tell this is a plan-lifecycle multiplexer rather than a plain delegation tool. It falls short of 5 because key terms ('bounded dependency plans', 'ordinary task admission') are undefined jargon and no sibling is named as a contrast.

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?

The action-to-parameter map implicitly tells the agent which action to pick for which operation (submit a spec, inspect a plan_id, list with offset/limit, cancel a plan), and 'Unknown outcomes wait for explicit resume' hints at when to follow up. However, there is no explicit when-to-use versus codex_delegate or codex_resume, and no stated preconditions or when-not guidance.

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