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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-redundant behavior: the return payload composition (cached and batch prices, context window, checked date) and the freshness model ('refreshed every morning'), which tells the agent how stale results can be.

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 dense sentences: the first front-loads the return contract and units, the second covers query semantics and refresh cadence. No filler, no restatement of the title, and the most decision-relevant information (what you get, how to search) comes first.

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 carries the return-value burden and does it well, listing units and the fields returned. Low complexity (2 params, read-only, no nesting) means little else is needed; only edge behavior such as no-match results or how multiple matched models are ordered/truncated is left unspecified.

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 100%, so the baseline is 3, with the schema already defining both params including the 1-25 limit range and default of 8. The description goes beyond that by giving example query strings that clarify the fuzzy matching semantics of 'query' (name vs id vs provider), which the schema does not convey.

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 names a specific verb and resource ('Today's API price for one or more large language models, in US dollars per million tokens') and enumerates what comes back (cached/batch prices, context window, checked date). It is unambiguous on its own, but it never contrasts itself with the closely related siblings llm_cheapest_models and llm_cost_estimate, leaving that differentiation to inference.

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?

It gives practical query guidance with concrete examples ('claude sonnet', 'gpt', 'gemini flash', 'deepseek'), which implies how to call it. However, it never states when to prefer this over llm_cheapest_models or llm_cost_estimate, nor any exclusions, so the usage boundary is only implied.

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