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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine context beyond that: every result carries a `status` whose four values are defined, including the important caveat that under_review text diverges from the official Planalto compilation and is not displayed. It does not discuss result ordering quality, empty results, or rate limits, which keeps it short of 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, both front-loaded: the first covers what is searched and what is returned, the second covers result interpretation. The status enumeration is long but each value carries decision-relevant meaning, so nothing is wasted.

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 an output schema present, the description need not enumerate return fields, and it still adds the one interpretation-critical nuance (status semantics). What is missing is modest but real: guidance on narrowing by `law`, behavior when no close matches exist, and any hint about how proximity is ranked.

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 100% and all three parameters (law, query, top_k) are documented in the schema itself, so the baseline of 3 applies. The description reinforces that `query` is a natural-language question rather than keywords, but adds nothing about the `law` restriction or `top_k` behavior.

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 states a concrete verb and resource ('Busca dispositivos de lei e súmulas') and the retrieval mode ('por uma pergunta em linguagem natural'), returning the closest matches with official links. It does not explicitly distinguish itself from the siblings get_precedent and get_provision, even though it overlaps them by touching súmulas and provisions, so an agent must infer that this is semantic discovery rather than direct retrieval.

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 by the phrase 'pergunta em linguagem natural', which suggests this is the tool for topical/descriptive queries, but the description never says when to prefer it over get_precedent or get_provision, nor does it state exclusions or prerequisites. The agent must derive the routing rule from the sibling names alone.

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