find

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds only that this is Outlook-backed search; it says nothing about the result cap (default 15, max 50), whether matches are ranked, or that an empty 'pasta' means a global sweep — details that matter for a search operation.

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, purpose first and trigger second, with no filler. The parenthetical '(busca do Outlook)' earns its place by identifying the search backend.

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?

No output schema exists

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 80%, so the baseline is 3. The description reinforces the field selection (texto/remetente/assunto mapping to the 'campo' enum), which adds a little meaning, but says nothing about 'periodo', 'pasta', or 'qtd' that the schema does not already carry.

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 and resource ('Busca emails') plus the searchable fields (texto, remetente, assunto) and the underlying engine (busca do Outlook), so an agent immediately knows this is an email search tool. It does not differentiate itself from any of the cryptic siblings (ls, cx, tag), leaving the agent to infer the boundary.

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 says when to reach for it: 'quando o usuário menciona alguém ou um assunto específico' — a concrete trigger condition. There is no when-not guidance and no named alternative for listing rather than searching (e.g., ls), so the guidance is clear but incomplete.

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