codex_models

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

Beyond the annotations (read-only, idempotent), the description adds: it's free, no model call, reads from cache or a bundled fallback (with `source` indicator), not fingerprint-stable, and that the payload matches the `codex://models` resource. It also warns that unlisted slugs may work and listed ones may be unavailable. No contradictions with annotations.

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 yet comprehensive. The first sentence clearly states the purpose. Subsequent sentences add crucial details about behavior, limitations, and usage advice. No fluff or 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 no parameters and an output schema, the description covers all necessary aspects: what the tool returns (list of model slugs), how it sources data, its reliability, and caching guidance. It also notes the equivalence to the codex://models resource.

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?

There are no parameters for this tool. The description mentions the `model` parameter in a different context (slugs to pass to it), which is helpful context but not about this tool's schema. Since schema coverage is 100% (0 params), baseline is 4.

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 that the tool lists Codex model slugs for use as the `model` parameter. It specifies it's free and makes no model call, distinguishing it from other codex tools that perform actions or queries.

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?

It explains when to use this tool (advisory discovery of model slugs) and provides important caveats: the list is from cache/bundled fallback, not authoritative, and validation happens via `codex exec`. It advises against caching by fingerprint. It doesn't explicitly mention alternatives, but the purpose is unique among siblings.

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