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

Goes beyond the readOnly/idempotent annotations with details those hints cannot convey: positions are rounded to about 1 km, nothing is stored, and the tool returns hits for regions with no pet listings so the agent is not misled by an empty result. That is exactly the kind of behavioral context annotations cannot provide.

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 the conversion action and followed by the caveat about uncovered places. The long example list ('Zaragoza, Wien or Fukushima') is somewhat wordy but does communicate accepted input variety and locale handling.

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 single-parameter resolver with no output schema, the description does convey what comes back (a point) and its precision, plus the edge case where no pets exist nearby. Only the exact response structure is unspecified, a minor gap.

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% and the single parameter's description repeats the same examples as the tool description, so no meaning is added beyond the schema. The description implies the accepted formats and the length cap is schema-side, so baseline 3 applies.

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?

Names a specific verb and resource ('Turn ... into the point find_pets would search around') and enumerates accepted input forms, so an agent knows exactly what it converts. It explicitly names the sibling tool (find_pets) whose input this feeds, distinguishing it from search/listing siblings.

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?

States the workflow context clearly: resolve the place first so the person can confirm it before find_pets runs. It also notes that unpets-covered places still resolve and that find_pets will report the absence, which prevents an agent from skipping the step. It does not name an explicit alternative for when not to call it, keeping it below a 5.

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