Lê uma página do acervo em Markdown, com as seções, as perguntas frequentes e as fontes oficiais com URL — é por elas que se confere o que a página afirma.
| Name | Required | Description | Default |
|---|---|---|---|
| caminho | Yes | rota canônica devolvida pela busca, com barra final (ex.: /consumidor/produto-com-defeito/) |
| Name | Required | Description | Default |
|---|---|---|---|
| titulo | Yes | ||
| caminho | Yes | ||
| markdown | Yes | ||
| url_canonica | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers safety, and the description adds meaningful context by specifying output format (Markdown) and contents (sections, FAQ, official sources with URLs). It also explains the purpose of sources for verification. There is no contradiction with annotations, and the description exceeds baseline by providing these details.
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 a single, front-loaded sentence that efficiently communicates the tool's action, resource, and output components. It is concise with no filler words, fully earning its place.
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?
Given the tool's simplicity (one parameter, output schema present), the description is complete. It explains what the returned page contains and even how to use the sources for verification, which complements the structured output schema and provides enough context for a correct invocation.
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 schema already provides full coverage (100%) for the 'caminho' parameter with a clear description ('rota canônica devolvida pela busca, com barra final'). The tool description adds no additional parameter semantics beyond the schema, so the baseline of 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 is specific and action-oriented: 'Lê uma página do acervo em Markdown' clearly states the verb and resource. It enumerates content components (sections, FAQ, official sources) and implicitly differentiates from the sibling search tool 'buscar_paginas' by focusing on reading a specific page.
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 context is provided through the parameter description mentioning 'rota canônica devolvida pela busca', which implies this tool is used after a search to fetch a page. The description also hints at verification purposes ('é por elas que se confere o que a página afirma'), but it does not explicitly state when not to use it or contrast with alternatives.
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.
Each tool serves a clearly distinct function: searching, reading, and reporting defects. There is no overlap in their purposes, and an agent would have no confusion about which tool to invoke for a given task.
All tool names follow a consistent verb-noun pattern in Portuguese (buscar, ler, relatar), making them predictable. The only minor inconsistency is the singular 'pagina' vs. plural 'paginas' in the objects, but this does not hinder understanding.
With only three tools, the server is tightly scoped to its purpose of searching, reading, and reporting issues in a legal collection. Each tool is essential and there is no bloat.
The server covers the core workflow of searching, reading, and reporting defects, which appears complete for its domain. The only gap is the lack of a way to browse or list pages without a specific search term, but this may be intentionally limited.
