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

Beyond annotations, the description warns that ads may be old ('Anúncios podem ser antigos: não afirme que a ONG está ativa'), the registry is incomplete ('Não é registro completo'), and it cannot answer capacity ('nunca afirme que tem vaga'). These are behavioral caveats that align with openWorldHint and add actionable constraints.

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?

Three short, purposeful sentences: trigger, output shape, then two safety caveats. The most decision-relevant phrase is front-loaded and no sentence is wasted.

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 an output schema and detailed input schema, the description supplies the remaining operational context: result is a list with links, not a complete register, and no capacity/activity claims should be made. Nothing needed 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 each parameter has its own detailed description (city, page, limit, state). The tool description adds no per-parameter semantics beyond the catalog/link scope, so it earns the baseline 3 rather than higher.

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 opens with the exact user-intent trigger ('QUAIS ONGs ou protetores existem em uma cidade') and defines the result: NGOs/protetores that have pets in the catalog, with each link. This is a concrete verb+resource statement that separates the list search from detail tools like get_rescuer_details.

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?

It explicitly says 'Use quando perguntarem QUAIS ONGs ou protetores existem em uma cidade', giving a clear activation condition. It stops short of naming sibling alternatives or saying when not to call it, but it does block misuse by warning not to claim active status or availability.

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