places_nearbyList points of interest near a location. Each one says whether it is open right now where that is known, so "is anything open near me" is one call
| Name | Required | Description | Default |
|---|---|---|---|
| lat | No | Optional latitude | |
| lon | No | Optional longitude | |
| near | No | Place to look around, e.g. 'Camden, London' (or give lat/lon) | |
| query | No | Optional keyword to filter by, e.g. 'cafe' | |
| radius | No | Optional radius in metres (default 1000) |
Changes observed during successful MCP inspections.
Input schema / properties / addressRemoved value: -{
- "description": "Address or postcode to search near",
- "type": "string"
-}Input schema / properties / lat / descriptionPrevious value: -"Latitude of the search location"New value: +"Optional latitude"Input schema / properties / lon / descriptionPrevious value: -"Longitude of the search location"New value: +"Optional longitude"Input schema / properties / nearAdded value: +{
+ "description": "Place to look around, e.g. 'Camden, London' (or give lat/lon)",
+ "type": "string"
+}Input schema / properties / queryAdded value: +{
+ "description": "Optional keyword to filter by, e.g. 'cafe'",
+ "type": "string"
+}Input schema / properties / radius / descriptionPrevious value: -"Search radius in metres, 100–5000 (default 500)"New value: +"Optional radius in metres (default 1000)"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds a genuinely useful behavioral trait: each result includes open-now status when known, and that 'one call' can answer the open-near-me question. There is no contradiction with annotations.
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 convey the tool's primary function and a distinctive behavior with no wasted words. The key use case is front-loaded, and the sentence structure is easy to parse.
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 read-only, idempotent tool with straightforward parameters, the description covers the essentials: location context, POI output, and openness detail. It does not mention response shape or pagination, but with no output schema and full parameter documentation, the remaining gaps are minor.
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 schema descriptions cover 100% of the parameters, so the baseline is 3. The description adds little beyond that baseline; it confirms the nearby-location concept and open-status behavior but does not explain parameter relationships or default radius. This is acceptable given the schema's completeness.
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 identifies the action ('List') and resource ('points of interest near a location'), plus the distinctive open-status feature. It does not explicitly contrast itself against sibling tools like places_search, but its purpose is evident and it works well as a discovery tool.
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 offers a helpful use case ('is anything open near me') but does not state when to prefer it over similar sibling tools such as places_search or places_geocode. No when-not-to-use guidance or alternative tool names are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.