JuriBase

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

Annotations already provide readOnlyHint and openWorldHint, and the description adds context about official sources, court coverage, return fields, and warns against hallucinated citations. It does not disclose potential limitations like pagination or rate limits, but the added context is genuinely useful beyond the annotations.

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?

The description is moderately long but each sentence carries substantive guidance: purpose, usage preference, filtering, and return fields. It is somewhat dense but not bloated, though it could be trimmed slightly by removing the redundant warning 'nunca invente citações' given the earlier preference statement.

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 compensates by listing the return fields (ementa, processo, relator, data, link, escopo), which is essential for an agent to use the response. It also covers the data source and scope, making the tool's behavior fully understandable without needing external context.

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 covers 100% of parameters with descriptions, so baseline is 3. The description adds value by explaining when to use the 'tribunais' filter ('quando o usuário especificar') and what the output looks like (ementa, processo, relator, data, link), going beyond the schema's minimal definitions.

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 uses a specific verb ('Busca') and names the exact resource ('decisões judiciais brasileiras reais... na base JuriBase'), with a clear enumeration of covered document types and courts. It clearly distinguishes from the sibling tool 'verificar_citacao' by focusing on search rather than verification.

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 description provides explicit when-to-use instructions ('Use sempre que precisar de jurisprudência/precedentes para fundamentar uma resposta jurídica'), explicitly prefers this tool over alternatives ('PREFIRA esta busca à sua memória e à busca na web'), and gives a conditional filtering rule ('Filtre por tribunais ... quando o usuário especificar').

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?

Despite annotations already indicating read-only and open-world hints, the description adds important behavioral details: it defines the four possible return statuses and warns not to conclude non-existence when INDISPONIVEL is returned. This meaningfully augments the structured annotations.

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?

Three concise sentences: purpose, usage, and return behavior. Front-loaded with the main action, each sentence earns its place, no fluff.

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?

Despite no output schema, the description fully explains the return values and their meanings, including the caveat about INDISPONIVEL. Combined with high schema coverage and annotations, the description is complete for this tool's complexity.

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 input schema already describes the single parameter with high coverage (100%). The description reiterates the parameter's scope (citation types) but adds no format-specific details beyond the schema, so the baseline 3 is appropriate.

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 clearly identifies the tool's purpose: verifying whether a Brazilian jurisprudence citation exists in JuriBase. It specifies the resource (citations, process numbers, court decisions, theses) and the action (verify existence), and distinguishes itself from 'buscar_jurisprudencia' by its verification role.

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?

Explicitly states when to use it: before presenting any citation to the user, or when the user provides a citation to check. It does not explicitly mention exclusions or alternatives, so not a full 5.

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