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

Annotations already declare read-only/idempotent/closed-world, so the description focuses on operational traits the annotations cannot convey: no live stock verification, no exchange rate applied, 'observed source price is not a current delivered offer', and the requirement to state the applied ranking rule and missing inputs. It stops short of describing pagination or result shape, but the behavioral context added is substantial.

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 but front-loaded: the trigger and filter translation come first, alternatives and negative scope follow. The trailing presentation instruction about linking model name to URL is useful but slightly off the tool's invocation purpose, keeping it from a perfect score.

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 13-parameter, zero-required, no-output-schema tool, the description does real work: it defines the return ('a short catalogue-based list'), mandates disclosing the ranking rule and missing inputs, and clarifies the price semantics. What remains thin is the exact result shape/pagination, but the essentials for correct invocation are present.

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 85% and several parameters carry their own descriptions. The description still adds meaning beyond the schema: query should contain only model/brand words rather than the whole conversation, a budget needs an explicit currency, and structured fields should be used instead of stuffing constraints into query. It does not cover every one of the 13 parameters, hence not a 5.

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 ('padel-racket shortlist') and enumerates exactly which filters (budget, brand, year, shape, playing priority) drive the search. It also distinguishes itself from the named siblings get_racket and compare_rackets, so an agent can route without opening schemas.

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?

Explicit when-to-use ('when a user wants a shortlist by...'), explicit when-not ('does not verify live stock, delivery, medical suitability or the whole market'), and explicit alternatives for adjacent needs ('For one model's evidence use get_racket; for two identified models use compare_rackets'). Nothing 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.