list_agent_models

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

With no annotations, the description fully carries the burden. It discloses that the tool uses different CLI backends (Codex, Antigravity, Claude Code), that Claude Code lacks a stable catalog so aliases are used, and that catalogs are enriched with local price tables where possible. It also clarifies that price_references[] is not an override and that provider/auth remain settings-level config. This is rich, honest behavioral disclosure.

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 structured with a lead sentence stating the core purpose, followed by targeted paragraphs explaining backend behavior and usage caveats. Every sentence adds value—no fluff or repetition. The length is appropriate for the complexity of the tool.

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?

Despite no annotations and an output schema that is not shown, the description explains what is returned (models[], price_references[]), how it behaves per agent, and how to use the output. It covers edge cases (Claude Code) and explicitly warns about the validity of price references. For a list tool, this is complete and self-sufficient.

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 0% for the two parameters (agent, project). The description says 'for one executor' which hints at the agent parameter, and mentions different agent CLIs, but does not explicitly explain 'project' or the default/resolution of 'auto'. The description adds some context but does not fully compensate for the absent schema descriptions.

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+resource: 'List likely selectable models for one executor, sorted high to low.' It clearly distinguishes this from sibling tools like list_projects (projects) and list_subagent_runs (runs), and the subsequent details about per-agent CLI backends reinforce the unique scope.

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 description says 'Pass a chosen models[].id to run_subagent(model=...)' which tells the agent exactly how to use the result. It also warns that price_references[] is context-only and not a valid override. However, it does not explicitly state when *not* to use this tool or select among alternatives, though the context implies it is the precursor to run_subagent.

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