list-models

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

No annotations are supplied, so the description carries the full disclosure burden, and it does meaningful work: it reveals the data source (the installed Codex CLI), the payload shape (model IDs plus reasoning effort levels), and that some models may be hidden from the picker. It does not state whether the call is cheap, whether it can fail when no CLI is installed, or whether results are cached, which are real gaps for a discovery prerequisite.

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?

Two sentences with no filler, and the statement of scope is front-loaded before the usage directive. Every clause conveys actionable information; nothing could be removed without loss.

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?

There is no output schema, so the description must convey return values, and it does so concisely (model IDs and reasoning effort levels). For a one-optional-parameter read tool this is nearly complete; only failure conditions and the hidden-model caveat at the top level rather than at the parameter level are left implicit.

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%; the single parameter includeHidden is fully documented in-schema as "Also list models the Codex CLI hides from its picker." The description text adds no additional parameter guidance beyond that. With the schema doing the heavy lifting, the baseline 3 is appropriate.

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 opens with a specific verb and resource: "List the model IDs and reasoning effort levels the installed Codex CLI supports." It also pins the scope to the installed CLI and names the two return values (model IDs, reasoning effort levels). No sibling tool (Help, ask-codex, batch-codex, review, version) does this, so the agent can distinguish it without opening a 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?

The second sentence gives explicit ordering guidance: "Call this before passing a model or reasoningEffort to other Codex tools." That is genuine when-to-use direction tied to a downstream action. It stops short of any when-not-to-use condition or alternative (for example, when a model is already known, or how this differs from a static hard-coded list), so it is clear but not exhaustive.

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