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

Annotations already declare readOnlyHint=true and idempotentHint=true, so description doesn't need to restate that. The description adds the bulk support behavior ('accepts ids for batched execution'), which is beyond annotations. It doesn't contradict annotations. However, it doesn't disclose details like error handling or return format, but with read-only annotation already provided, the bar is lower. So 4 is justified.

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 very short: two sentences. It is front-loaded with the main purpose. The bulk support is added as a second sentence. No unnecessary words. It earns its place. Slightly under-specified, but for its length, it's concise. Score 4.

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 has 3 parameters, one required, and one parameter is a nested object (query) with zero explanation, the description is incomplete. It doesn't mention what the query object does, nor does it provide details about the response (no output schema). For a 'get' tool with batch support and a query object, the agent would need more info. Also, the bulk support is mentioned but not elaborated (e.g., how errors are handled). So completeness is low. Score 2.

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%, meaning the description provides no parameter explanation. The description only mentions 'id' and 'ids' for bulk support, but the schema shows a 'query' parameter as an object, which is completely unexplained. With zero coverage, the description should compensate, but it only covers id/ids, not query. This is a significant gap because the query object likely allows complex filtering, which the agent needs to know. So score 2.

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 this tool fetches a lawsuit by ID and returns complete data. It also mentions bulk support. The purpose is clear and distinct from sibling tools like advbox_list_lawsuits (which lists multiple) and advbox_get_customer (different resource). Slight deduction for not explicitly contrasting with sibling list/get tools, but the verb 'Busca' (searches/fetches) and 'por ID' specify the operation.

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 implies usage: use this tool to fetch a single lawsuit by ID, with option for batch via 'ids'. It does not explicitly say 'when not to use' or mention alternatives, but within the sibling set, it's clear that this is the get-by-ID tool. Sibling names like advbox_list_lawsuits suggest alternatives, but not explicitly stated in the description. So guidance is implied rather than explicit.

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