Find nearby places (POIs)

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds behavioral details beyond those: results are sorted by distance, and category filters accept both predefined shortcuts and arbitrary OSM key/value pairs. It does not describe pagination or rate limits, but given the output schema exists and the tool is read-only, this is a reasonable level of disclosure.

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 efficiently structured: it opens with the core purpose, then provides the category shortcut list (which is necessary for usability), and closes with a pointer to the sibling tool. Every sentence serves a purpose – no fluff. The long list is justified because it enumerates valid values that are not in the schema.

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 the tool's complexity (5 parameters, 2 required) and the existence of an output schema, the description covers all critical aspects: what it does, how to filter (categories, OSM tags), and where to go for more detail. It doesn't explain default values for limit, radius_m, or language, but those are documented in the schema. The description is complete for an agent to correctly invoke the tool and interpret results (with output schema).

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?

While the input schema covers 100% of parameters, the description adds substantial semantic value, especially for the category parameter. It lists dozens of valid shortcuts (restaurant, cafe, museum, etc.) and explains the OSM tag syntax ('key' or 'key=value'). It also clarifies that 'near' can be coordinates or place names, reinforcing the schema but with practical guidance. This is far beyond baseline for a schema-covered parameter.

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 clearly states 'Finds points of interest near a location, sorted by distance' – a specific verb, resource, and sorting behavior. It also distinguishes itself from poi_details by pointing to that tool for full records, and from geocode/reverse_geocode by implying location lookup is integrated. The category shortcuts and OSM tag syntax further clarify the exact scope of what can be searched.

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 names an alternative ('Use poi_details for the full record of one result') and gives a condition for when to switch. While it doesn't enumerate exclusions for every sibling (e.g., suggest_meeting_point, isochrone), the core purpose is unambiguous enough that an agent can infer when to use this tool versus those. The description also clarifies that arbitrary OSM tags can be used, expanding the tool's applicability.

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