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

Annotations already disclose readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description doesn't need to repeat those. It adds valuable behavioral context: the tool expects pre-clipped geometry and fails or misbehaves if given a CONUS HeatRisk dissolve, plus it notes that classes filter a civic allowlist. This goes beyond the structured annotations with practical 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?

The description is compact: one purpose sentence, one warning/alternative sentence, one classes sentence, and an example. Every sentence adds distinct value—purpose, exclusion, parameter behavior, and a concrete illustration—without repeating schema content or padding. The example is long but earns its place as a callable template.

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?

The tool has an output schema, so return values need no explanation. Annotations cover safety traits, the schema documents both parameters, and the description adds the prerequisite, an alternative, and an example. Given the modest complexity (two params, one nested object), nothing an agent needs 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%, so the baseline is 3. The description adds extra meaning by warning against a specific problematic input ('do not pass a CONUS HeatRisk dissolve') and by providing a full JSON example that demonstrates the geometry and classes structure. The example hands an agent a concrete usage template beyond the schema's field descriptions.

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 'Civic POIs (schools, hospitals, airports, …) inside a caller-supplied GeoJSON Polygon or MultiPolygon', which names the resource (civic POIs), the operation (find inside a polygon), and the input type. It also distinguishes itself from get_alerts by stating that get_alerts is for NWS alerts and already includes POIs, giving agents a clear basis to choose this tool over a sibling.

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?

The description provides explicit when-to-use and when-not-to-use guidance: 'For an NWS alert use get_alerts({alert_id}) (already includes pois)' is a direct alternative, and 'Clip first — do not pass a CONUS HeatRisk dissolve' gives a concrete prerequisite with a negative example. This tells an agent exactly when to pick this tool versus another and how to prepare input.

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