list_models

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

With no annotations at all, the description carries the full burden and does well: it discloses the shape of returned data (thinking levels, price per million tokens with null for unknown/local, policy allowance), notes that tiers are recomputed from a live catalog, and flags that refresh triggers a provider re-fetch — a real side effect. It omits an explicit read-only/no-mutation statement and says nothing about volume or latency of the full catalog listing.

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?

One front-loaded summary sentence establishes scope, then labeled lines give per-engine and per-parameter detail with zero filler. Each line contributes information an agent needs before calling.

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?

For a three-optional-parameter read tool with no output schema and no annotations, the description explains the return payload well enough to call confidently and interprets every parameter. What remains missing is a note on whether the tool is purely read-only and any expectation about response size when many providers are configured.

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%, so the description must compensate and largely does: it documents the semantic difference between engine=omp and engine=claude, defines filter as a case-insensitive substring with examples, and explains refresh as re-fetching catalogs first. The only gap is that default values and the fact that all three parameters are optional come from the schema rather than the prose.

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 opening sentence names the resource precisely (models on this machine plus current automatic tiers), and the per-engine lines specify what is returned for omp versus claude, including thinking levels, pricing, and policy allowance. It never explicitly contrasts itself with the model-policy siblings (get_model_policy/set_model_policy) that it references indirectly.

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?

Guidance is parameter-level rather than tool-level: the filter line gives concrete example substrings and the refresh line explains when to trigger a re-fetch. There is no statement of when to call this instead of get_model_policy or any other model-related tool, so selection is left to inference.

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