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

Annotations already establish safe read-only, idempotent, closed-world behavior, so the description's job is to add context — and it does, disclosing the return shape: how the phrase was parsed, the total count, and the first results with rating, checked price range, and a link to the wine's record. That parsed-query feedback is behavior an agent cannot get from annotations or schema. It stops short of describing empty-result or failure behavior, keeping it below a 5.

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 sentences, front-loaded with the core capability and examples, with no filler. The bilingual restatement at the end is somewhat redundant for a Portuguese-speaking agent but earns its place as a quick language hint for others.

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-parameter read-only search tool with no output schema, the description covers what the tool does, how to phrase input, and what comes back. Minor gaps remain around result-empty handling and how price-range 'conferida' filtering behaves, but nothing essential to calling it correctly 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 100%, so all three parameters are already documented, including the enum and the 1–10 bound on quantos. The description adds only that the phrase should be spoken-style natural language rather than keywords, and that Portuguese tends to work best — modest but real meaning beyond the schema, so the baseline 3 fits.

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 gives a specific verb and resource — natural-language wine search over ~50k labels using the same engine as the site — and the examples ('tinto pra bacalhau até 150 reais') make the input shape unmistakable. It does not explicitly name or exclude a sibling such as buscar_no_site or ficha_do_vinho, so an agent still has to infer that this is phrase-level discovery rather than lookup or site-wide search.

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?

Usage is implied through concrete example phrases and the note that Portuguese works best, which tells the agent how to phrase a query. However, there is no explicit when-to-use versus alternatives guidance (e.g., 'use ficha_do_vinho once you have a specific label' or 'use buscar_no_site for non-wine content'), leaving routing to inference.

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