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

Annotations already establish readOnly/openWorld/no-destructive, and the description adds genuinely new behavioral context: entries are hand-verified and dated, coverage is partial and city-by-city, and the response may legitimately be empty. That empty-result disclosure is valuable operational context. It stops short of explaining freshness guarantees beyond 'com data' or any rate/latency behavior.

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 sentences, front-loaded with what the tool returns, followed by the filtering and coverage caveats. No filler, no repetition of the title, and every clause carries information.

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 shape need not be described, and the description covers the non-obvious risks: partial geographic coverage and possible empty responses. A note on result freshness or on what to do when the city is ambiguous would complete it, but the essentials are present.

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 100%, so city, need, limit and state are all fully documented in the schema itself, including the ambiguous-city error behavior and the enum-like need values. The description only restates the need filter ('Filtra por necessidade') and adds nothing beyond the structured fields, which is the expected baseline.

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+resource ('serviços públicos para animais numa cidade') and enumerates exactly what is covered: public/university veterinary hospital, zoonoses, castration, municipal animal welfare and complaint channels. That enumeration cleanly separates it from siblings like search_pets, search_rescuers and get_city_stats without needing to name 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?

'Filtra por necessidade' implies the need parameter drives selection, and the note that coverage is partial and the response can be empty hints at expected conditions. However, it never says when to use this tool versus siblings, nor what an agent should do when the result comes back empty, so usage is only implied.

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