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

Annotations already declare the safe read-only, idempotent, non-destructive profile, so the bar is lower; the description still adds the return shape (number, órgão, data, situação, texto/ementa, official link) and the non-obvious fallback that a court without native search returns an officialSearch link instead of results. It does not mention result limits, pagination, or latency, which for an open-world search tool would have been useful.

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 verb and the "not web search" differentiator, then the source inventory. The long enumerated clause carries genuine routing information but is dense enough that it reads as a list dump; a small structural split would have helped.

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 correctly compensates by naming the fields each precedent returns, and all three required parameters are documented in the schema. The omission of result-count or pagination behavior for a search tool is the only material gap.

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% and the schema itself already documents the enum meanings, the sigla format, and the "Tema 929"/"Súmula 479" query pattern. The description restates the scope groupings and court behavior rather than adding syntax, limits, or examples the schema lacks, so the baseline 3 applies.

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 a specific verb ("Pesquisa") and resource (official Lauda jurisprudence databases) and enumerates exactly which corpora each scope covers, so the agent knows what will and will not be searched. It also distinguishes itself from the generic web search path ("sem passar pela busca web"), which is the only plausible alternative given the sibling tools are all calculators/lookups.

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?

The opening clause tells the agent this replaces a web search for case law, and the parentheticals map each scope value (qualified, stj, state) to the sources it covers, which is real routing guidance. It never states an explicit "do not use when" condition or a prerequisite (e.g., query must be anonymized — that only appears in the schema), so it stops short of a 5.

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