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

Annotations already declare readOnly/non-destructive, but the description goes well beyond them: it discloses that this is the slowest call, that it consumes the firm's daily analysis budget (a real rate/cost constraint), that it reads full text or excerpts depending on fit, and that citations are verified against the page. This is exactly the operational context an agent needs before spending budget.

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 tight sentences: the first front-loads what the tool does and what it returns, the second delivers the cost/sequencing guidance. Every clause earns its place with no filler.

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 having no output schema, the description explains the return ('a resposta com cada citação conferida contra a página'), the cost profile, and the routing. Nothing an agent needs in order to call it correctly is missing.

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% and the modo enum is already documented, so the baseline is 3. The description adds meaning by explaining the full-text-versus-excerpt behavior ('o texto inteiro quando cabe; senão, os trechos mais relevantes'), which clarifies the operational consequence of the modo choice beyond the raw enum values.

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 (answers a question) and resource (a case's autos), and explicitly distinguishes itself from siblings by naming buscar_autos and ler_paginas as the lighter alternatives. An agent can tell what it does and how it differs from the other case-reading tools without opening any 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 explicit sequencing ('use depois de processo_status') and a routing rule ('para fato pontual, prefira buscar_autos ou ler_paginas'). Both when-to-use and when-to-prefer-a-sibling are stated directly, leaving nothing to inference.

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