triagem

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

With no annotations provided, the description carries the full disclosure burden and does well: it states it scans all boxes, aggregates entries from the last N days, summarizes only documents for cases with judicial integration, does not download PDFs, and explicitly declares 'Leitura passiva: não toma ciência nem executa passo de fluxo' (passive read, no state change). It doesn't mention rate limits or error conditions, but the core side-effects and output expectations are clear.

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 two sentences long, front-loads the tool's purpose ('TRIAGEM em uma chamada'), and every clause earns its place: scanning all boxes, time-window, judicial integration filter, summary content (description/date), and absence of PDF downloads. No fluff or repetition.

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?

The tool is a read-only triage/aggregation function with three optional parameters and an output schema (not shown). The description covers the full scope: all inboxes, time window, filtering by judicial integration, what is summarized, what is omitted (PDFs), and that no workflow action is taken. With an output schema present, the description need not detail return formatting, making this sufficiently complete.

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 0%, so the description must compensate for the three parameters. It explicitly explains the 'dias' parameter in context ('nos últimos `dias` dias'), but does not mention 'max_processos' or 'max_documentos' by name. These names are self-explanatory and the description implies limits via 'para cada processo... resume os documentos mais recentes', but full compensation is not achieved.

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 strong verb 'varre' (scans) and specifies the scope: all mailboxes, gathering items from the last 'dias' days and summarizing recent documents per process. It clearly distinguishes from siblings like listar_caixa (single box) and baixar_documento_judicial (downloads PDFs) by explicitly stating it does not download PDFs and is a passive read-only briefing.

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 states the use case: 'TRIAGEM em uma chamada — briefing da caixa do procurador' (one-call triage to get a prosecutor inbox briefing). It implies when to use it (quick overview) and contrasts with alternatives by noting it scans all boxes without downloading files or executing workflow steps. However, it never explicitly names sibling tools as alternatives or gives a 'use X instead' directive.

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