find_locationResolve a place name to latitude and longitude for location-based weather data; if several places match, ask the user to choose the correct one.
Latitude and longitude of a place (OpenStreetMap Nominatim). If several match, ask the user which one.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Place name, e.g. 'Kopaonik' or 'Lisbon, Portugal' |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint and openWorldHint, so external-service behavior is partly covered. The description adds the data source and the multi-match/user-disambiguation behavior, which are genuinely beyond the annotations, but says nothing about rate limits, result ordering, or failure behavior for unmatched names.
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 short sentences with no filler. It front-loads the return value rather than the action, which is slightly backwards for tool selection, but nothing 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?
An output schema exists, so the description does not need to explain return values, and it covers the main risk (ambiguous matches) an agent must handle. The remaining gap is the undocumented limit parameter and whether results are ranked.
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 only 50%: query is documented with examples in the schema, but limit has no description anywhere. The phrase 'if several match' hints that multiple results can come back, which indirectly relates to limit, but the description never explains limit's range or effect.
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 states the resource (coordinates of a place) and names the geocoding backend (OpenStreetMap Nominatim), so an agent knows exactly what it gets back. The verb is implicit rather than stated ('Latitude and longitude of a place' rather than 'Geocode a place name'), and it does not distinguish itself from the sibling find_area, which is likely the nearest alternative.
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 gives one concrete operational rule — 'If several match, ask the user which one' — which is real guidance for disambiguation. But it never says when to use this rather than find_area or when coordinates are a prerequisite for get_weather / request_point_history, so the choice among siblings is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.