Busca no acervo jurídico brasileiro e devolve id, título e URL de cada página. Formato padrão de conector (o mesmo de fetch); para área e trecho, use buscar_paginas.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | pergunta ou termos em português sobre direito brasileiro |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, covering the safety profile. The description adds that it returns id, title, and URL, and mentions 'standard connector format' which hints at output structure. It doesn't disclose pagination or rate limits, but with readOnlyHint and an output schema present, the additional value is moderate.
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 concise sentences with the primary action and return format front-loaded, followed by a clear routing instruction. No wasted words.
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 single-parameter search tool with an output schema and annotations covering safety, the description covers the essential behavior and distinguishes the sibling. It lacks explicit pagination details, but that's a minor gap given the simplicity.
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%, so the query parameter is already documented. The description adds no extra semantics beyond what the schema provides, so 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 states the tool searches the Brazilian legal collection and returns id, title, and URL for each page. It explicitly contrasts with buscar_paginas for 'área e trecho', distinguishing it from a sibling tool.
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?
It provides a clear alternative ('use buscar_paginas') for a different use case (area and excerpt), giving guidance on when not to use this tool. It doesn't elaborate on other contexts, but this is sufficient for the primary distinction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The set has two overlapping pairs: search/buscar_paginas and fetch/ler_pagina both address searching and reading, which could confuse an agent. The descriptions do provide some separation—one pair is the standard connector format and the other is subject-oriented—but the boundaries are not immediately obvious from names alone.
Naming mixes Portuguese snake_case verbs (buscar_paginas, ler_pagina, relatar_defeito, responder_pergunta) with English bare names (fetch, search). This inconsistent language and style makes the tool set feel less predictable and harder to navigate.
Six tools is a well-scoped size for this domain. Each tool serves a plausible purpose: two search variants, two read variants, a defect reporting flow, and a question-answering flow. The count is neither bloated nor too thin.
The surface covers the core lifecycle of this read-only legal collection: discover pages, retrieve content, verify sources, submit defect reports, and ask grounded questions. No major operation appears to be missing for the stated purpose.
