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

Beyond readOnlyHint it discloses that no authentication is required, that prices are OpenRouter reference prices that may differ from a provider's direct pricing, that the catalog refreshes every 15 minutes, and how unknown ids are handled (similar-id fallback). These are exactly the operational caveats an agent needs and none are repeatable from the 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?

Front-loads the resource and returned fields before modes and usage triggers, and every sentence carries distinct information. It is a dense single paragraph that runs long, but no sentence is padding.

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 compensates by enumerating every returned field (prices, context window, max output tokens, knowledge cutoff, modalities, retirement date, status enum values). Nothing needed to call or interpret the result is missing.

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 coverage is already 100%, so parameter syntax is covered; the description still adds semantic detail the schema lacks, namely that provider/query return up to 40 matches and that an unknown model_id yields a list of similar ids. The model_id precedence rule is stated in both places, so it is only mildly additive.

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?

Opens with a specific verb+resource ('Looks up AI models in the OpenRouter catalog') and enumerates exactly which fields are returned. It is clearly distinguishable from sibling tools like package_status or eol_status, which cover packages and end-of-life data rather than model catalog entries.

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?

Names four concrete triggers ('before writing a model ID in code, choosing between models, estimating costs, or checking whether a model is being retired') and an explicit exclusion ('It does not call, run or benchmark models'). The two invocation modes (single model_id vs. provider/query search) are also stated as conditions.

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