local-agent-mcp

by ezra-y

Overview Schema Source Related Servers Discussions Admin

Python

Local

Ask local Codex

ask_codex

Read-only

Start a read-only Codex job asynchronously and receive a job ID to retrieve the result later.

Instructions

Start a read-only local Codex job and return its job ID immediately.

The project is a path relative to the configured Codex root. The server rejects paths outside that root and always runs Codex in read-only mode. Use get_codex_job to retrieve the final result.

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": {
      "prompt": "<prompt>"
    },
    "name": "ask_codex"
  }
}

Input Schema

Name	Required	Default
`prompt`	Yes
`attempt`	No
`project`	No	.
`step_id`	No
`workflow_id`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.1Aug 24, 2026

TDQS

A4.1/5.0

Behavior4/5

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

The description adds valuable behavioral details beyond the annotations: 'always runs Codex in read-only mode' (redundant with readOnlyHint but reinforces) and 'server rejects paths outside that root' (security constraint). It also discloses that it returns immediately and that retrieval is separate, implying asynchronous behavior. This complements the annotations, which already cover read-only safety.

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?

The description is compact and well-structured: the first sentence states the core action immediately, followed by a second sentence clarifying constraints and the follow-up retrieval path. No redundant wording, and it front-loads the most important information first.

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?

The tool has 5 parameters and an output schema, but only 'project' is explained. The description omits guidance on 'attempt', 'step_id', and 'workflow_id', which could be crucial for workflow integration. While the return value is hinted (job ID) and the output schema likely covers it, input-side completeness is lacking for an agent to invoke correctly with intent.

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?

With schema description coverage at 0%, the description must compensate for parameter explanations. It only addresses 'project' ('The project is a path relative to the configured Codex root'). The other parameters (prompt, attempt, step_id, workflow_id) remain unexplained, limiting an agent's ability to set them correctly.

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

Purpose5/5

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

The description clearly states the tool's action: 'Start a read-only local Codex job and return its job ID immediately.' It specifies a distinct verb, resource type, and return value. By pointing to get_codex_job for retrieval, it distinguishes its role from that sibling, making the purpose unambiguous.

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?

The description provides clear usage context by noting the project path constraint and read-only mode, and explicitly directs to use get_codex_job to retrieve results. However, it does not explicitly contrast with other start-like siblings (e.g., start_codex_job or start_codex_turn), so an agent may not know when to prefer this tool over those alternatives.

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