Skip to main content
Glama

codex_goal

Destructive

Read, set, or clear a task goal—including objective, status, and token budget—while requiring explicit user approval and an operation key for changes.

Instructions

get reads a goal; set takes objective/status/token_budget; clear removes it. Mutations need user_requested=true and an operation key. Only change goals on explicit human instruction.

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_goal"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoget
statusNo
task_idYesTask id
objectiveNo
request_idNoKey for identical retries
operation_idNoAlias of request_id
token_budgetNo
user_requestedNo

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the bar is lower, yet the description adds real value: it states that clear removes the goal outright and that mutations are gated behind user_requested=true plus an operation key. It does not explain retry/idempotency behavior of the operation key or what token_budget actually governs, so it is strong but not complete disclosure.

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

Conciseness5/5

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

Three compact sentences, front-loaded with the action map, then prerequisites, then the safety policy. No filler, no restatement of the tool name, and the ordering puts the highest-value routing information first.

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

Completeness4/5

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, and the mutation preconditions plus human-instruction policy cover the riskiest behavioral aspect of this 8-parameter tool. Remaining gaps are minor: no description of token_budget behavior or of what happens on a duplicate operation key.

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 coverage is only 38%, so the description must compensate — and it does, mapping objective/status/token_budget to the set action, explaining the operation key (request_id/operation_id) as a mutation requirement, and clarifying the user_requested gate. The main gap is token_budget semantics (what the budget limits) and status-transition rules.

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 names the resource (a goal) and enumerates the three operations it multiplexes: get reads, set writes objective/status/token_budget, clear removes. An agent can tell exactly which action enum value does what. It stops short of differentiating itself from nearby siblings like codex_get or codex_status, so it lands at 4 rather than 5.

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

Usage Guidelines4/5

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

It gives a concrete precondition for the risky path ('Mutations need user_requested=true and an operation key') and a policy constraint ('Only change goals on explicit human instruction'), which directly shapes when an agent may call set/clear. It offers no explicit alternative-tool routing, but the when-to-use and when-not-to-use signals for the mutating actions are clear.

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