llm_codex

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

Discloses that the tool runs non-interactively and uses the user's OpenAI subscription (not Claude quota), which are important behavioral traits. Without annotations, this adds value, though it omits details on prerequisites, error handling, or state changes.

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

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

The description is concise, with a clear first-line purpose, followed by essential details and a structured Args section. Every sentence contributes information without redundancy.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, output schema exists), the description covers core functionality, usage guidelines, and parameter semantics. It is nearly complete, though it could mention prerequisites like local Codex installation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explains both parameters: 'prompt' as 'the task or question' and 'model' with a default and list of available models. This adds meaning beyond the schema's type-only definitions, compensating for the 0% schema description coverage.

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

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

The description clearly states it routes a task to the local Codex desktop agent (OpenAI) and runs non-interactively. It differentiates from other llm_* tools by specifying it uses the user's OpenAI subscription and lists available models, making the purpose specific and distinct.

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

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

Explicitly says 'ideal as a fallback when Claude limits are tight, or for tasks that benefit from OpenAI's models,' providing clear when-to-use context. Also contrasts with Claude quota usage, helping an agent decide between this and other LLM tools.

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