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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds the material fact annotations cannot carry: '$0.002/call', which is essential for a metered tool. It also discloses the return payload structure, which helps the agent decide before paying. It stops short of stating catalog freshness or result truncation behavior.

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?

Dense, front-loaded, and every clause carries information: item shape first, then filters, then sort, then price, then purpose. The telegraphic style leans on shorthand but remains parseable. No filler sentences.

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's item field list is doing necessary work and it delivers the fields an agent needs to compare models (per-1M input/output pricing, context, max_output, capability flags). Cost, filters, sorting, and usage are all covered; only `limit` is missing, which is minor.

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 carries the burden and largely meets it: it enumerates the accepted `needs` values (tools, json, vision, reasoning, audio, pdf) and the `sort` modes, plus provider and min_context intent. The `limit` parameter (1-100, the only bounded param) is never mentioned, which is a real omission for result sizing.

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?

States the specific resource and scope precisely: '~450 LLMs' with a defined item shape (id, provider, context, max_output, input_per_1m, output_per_1m). It does not differentiate itself from siblings ai_cheapest and ai_cost, which cover overlapping price-comparison ground, so an agent can't tell from the description alone which to call.

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?

'Use to list or filter LLMs by price, context and capabilities' gives implied usage, and the sort/filter options hint at when it's appropriate. But with ai_cheapest and ai_cost in the sibling set, the description never says when this catalog tool is preferred over those narrower price tools, leaving the routing decision to inference.

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