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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful non-obvious behavior: the tool accepts a raw Elasticsearch body and has a 10k pagination ceiling, recommending search_after. This meaningfully supplements the annotation baseline without contradicting it.

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 short sentences: the first establishes the tool's purpose and advanced/escape-hatch nature, the second gives the critical pagination caveat. No filler, no repetition of schema or annotation data.

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 6-parameter tool with no output schema and 0% parameter coverage, this is too thin. It does not describe the response shape, default page size, required query DSL knowledge, or how this tool relates to datajud_search. An agent invoking it correctly would still need to infer several important details.

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 carries real weight. It clarifies that 'query' is a raw Elasticsearch query body and explains the purpose of 'search_after'. However, it does not explain from, size, sort, or how 'tribunal' selects the target index, though those are partially inferable from names and the enum.

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 specific verb ('envia') and resource ('corpo de query Elasticsearch cru pro índice do tribunal'), and characterizes the tool as an 'escape hatch'. This clearly separates it from the higher-level datajud_search and datajud_get_processo siblings, even without naming them.

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 terms 'Avançado' and 'escape hatch' imply that this tool is for cases where normal search tools are insufficient, and the instruction to use search_after beyond 10k gives concrete usage guidance. However, there is no explicit statement about when not to use it or which sibling should be preferred for standard queries.

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