JuriBase

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

Annotations already declare readOnly, openWorld, and non-destructive behavior, so the safety profile is covered. The description adds real value beyond that: it warns against inventing citations, states that results carry official sources, and enumerates the returned fields. It does not discuss rate limits or result-count/pagination behavior, keeping it from 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?

Front-loaded with the core action and source scope, then the usage hint, then the anti-fabrication guardrail, then the return fields. Multiple sentences but each earns its place; only slight redundancy between the source list and the scope-mentioned return field.

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?

No output schema exists, yet the description enumerates what comes back (ementa, processo, relator, data, link, scope), and annotations cover safety. Combined with fully documented parameters, an agent has everything needed to call and interpret it correctly.

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 both parameters are fully documented with examples in the schema itself. The description restates the court-filter example but adds no syntax or format detail beyond what the schema already provides, so 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 (busca) and richly specified resource: real Brazilian court decisions (acórdãos, súmulas, teses, repetitivos) from JuriBase across named official sources. The scope and source coverage make it unmistakably different from a citation verifier, so an agent can route correctly without opening the schema.

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?

Gives clear when-to-use guidance ('útil para encontrar jurisprudência/precedentes que fundamentem uma resposta jurídica') and a conditional rule for the tribunais filter. It does not explicitly name verificar_citacao as the alternative or state when-not to use it, so it stops short of full routing guidance.

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

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

Annotations only declare read-only and open-world; the description adds the much more valuable behavioral layer: the four result states, the fact that DIVERGENCIA means the citation exists with different data, and an explicit warning not to infer non-existence from INDISPONIVEL. The covered-scope caveat further tells the agent how to interpret a NAO_ENCONTRADO.

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?

One dense paragraph, front-loaded with the purpose before the usage and result semantics. Every sentence earns its place, though the result enumeration plus parentheticals makes it slightly heavy for a single-parameter tool.

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 must carry return semantics, and it does so completely: all four statuses are defined with their interpretation traps. Combined with the scope note, an agent can call this and act correctly on any response.

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?

The single parameter is fully documented in the schema (100% coverage), so baseline is 3, but the description adds accepted input forms beyond the schema's generic wording: processo number, acórdão, or tese. Minor added value, no format examples.

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 (verificar) plus the resource (citação de jurisprudência brasileira) and narrows to the JuriBase official-source database, so the agent knows exactly what is being checked. It does not name the sibling buscar_jurisprudencia or contrast existence-checking with searching, so it falls short of a 5.

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?

Gives concrete triggers: before presenting a citation to the user, or when the user supplies a citation to check. That is clear context for use, but it never states when NOT to use it or points to buscar_jurisprudencia as the alternative for exploratory searches.

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