Search UK Ordnance Survey Points of Interest by text, with an optional bounding box to filter results by location.
Search OS Points of Interest by text, with optional bbox filtering.
| Name | Required | Description | Default |
|---|---|---|---|
| bbox | No | [minLon,minLat,maxLon,maxLat] | |
| text | Yes | POI search text | |
| tool | No | ||
| limit | No |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | ||
| results | Yes | ||
| provenance | No |
Changes observed during successful MCP inspections.
v0.8.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, covering the safety profile. The description adds the behavior that bbox filtering is optional, but otherwise does not disclose additional runtime behavior such as result ordering, defaults, or limits. No contradiction with annotations exists.
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 a single front-loaded sentence with no filler. It communicates the core action, target data, and key optional parameter in minimal words, which is ideal for quick agent parsing.
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 rich annotations, output schema, and simple parameter set, the description covers the essential selection and invocation details. It lacks explicit note about the limit parameter's semantics, but the schema already bounds it, so no critical information is missing for correct invocation.
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?
The description adds light semantic context by identifying 'by text' and 'optional bbox filtering', which maps to the text and bbox parameters. However, the limit parameter has no description in either the schema or the description, and the tool parameter is self-evident, so the description only partially compensates for 50% schema coverage.
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 a specific verb ('Search'), a resource ('OS Points of Interest'), and the query mechanism ('by text'), with optional bbox filtering. This is enough to distinguish it from siblings like os_poi_nearest or os_poi_within, although it does not explicitly 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?
The phrase 'by text' implies the tool is for textual POI search, and 'optional bbox filtering' provides some usage context. However, there is no explicit guidance on when to prefer this tool over siblings such as os_poi_nearest or os_poi_within, nor any mention of exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.