buscar

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

Annotations already declare readOnly/idempotent/closed-world, so safety is covered. The description adds real behavioral context beyond that: the returned index fields (#id, caminho, seção, ~tokens), the query filter syntax (pasta:, tipo:, tag:, desde:, -excluir, exact phrase), and that `detalhado=True` yields larger excerpts.

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?

Front-loads the core capability, then compresses filter syntax and the follow-up workflow into two dense paragraphs. Nearly every clause earns its place, though the inline filter list is terse enough to risk ambiguity.

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?

An output schema exists, so return structure need not be explained, yet the description usefully characterizes the index and the follow-up path. Complete enough for correct invocation, missing only the semantics of `limite`.

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 0%, so the description must carry all parameter meaning. It documents `detalhado` well and implies the query semantics of `consulta` via the filter syntax and natural-language phrasing, but `limite` (result count) is never mentioned, leaving a real gap.

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 ('Busca') and two distinct modes (keyword and semantic, accepting natural-language questions), plus what it returns (a compact index). An agent can distinguish this from siblings like `filtrar`, `recentes`, or `onde` 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?

Explicitly prescribes the workflow: it returns an index of what to open, then says to use `ler` (with `secao`) or `ler_varios`. Names the alternatives by name and the condition selecting each, 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.