List Codex models

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower. The description still adds meaningful behavior: the catalog is read from the installed Codex CLI and 'never hardcoded,' which tells the agent results reflect the local environment. It also implies caching via the refresh parameter's semantics.

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?

Three short sentences, each carrying distinct information: what is returned, where the data comes from, and when to call it. Front-loaded with the core action and no 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?

With no output schema, the description does describe the content of the return (models and their reasoning-effort levels), covering the essential shape. It doesn't detail the exact structure or the case where the CLI is absent, but for a single-optional-param read tool this is close to complete.

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?

Schema description coverage is 100% and the single 'refresh' parameter is fully documented there as bypassing the cache. The description adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

Specific verb+resource ('List the Codex models available on this machine') plus the scope of what is returned ('reasoning-effort levels each one supports'). It also names the sibling it relates to (codex_delegate), so an agent can distinguish it from the other codex_* tools without opening the schema.

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 states the trigger: 'Call this before codex_delegate when choosing a model explicitly.' That gives a clear when-to-use tied to a named sibling. It stops short of stating when-not-to-use (e.g., when a default model is fine), so it's not fully exhaustive.

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