ThinAir Geo

search_places

Read-onlyIdempotent

CATEGORY-specific POI search near a point — gas stations, truck stops, restaurants, charging stations, etc. Use this when the user has a specific TYPE of place in mind (food / health / retail / fuel / accommodation / nightlife / transport / government / recreation). For broader DISCOVERY (e.g. 'cities within 50 miles' or 'venues by population'), use explore instead.

Input Schema

TableJSON Schema

Name	Required	Description
`lat`	No	Center latitude (alternative to `center` object)
`lon`	No	Center longitude (alternative to `center` object)
`limit`	No	Max results (default 10, max 50)
`query`	No	Free-text place query such as 'truck stop', 'restaurant', 'charging station'
`center`	No	Center point for nearby search ({lat, lon} object or JSON string). You can also pass flat lat/lon.
`layers`	No	Restrict to: venue, address
`radius_m`	No	Search radius in meters (default 1000, max 50000)
`categories`	No	Structured categories: food, fuel, charging_station, education, health, entertainment, retail, accommodation, nightlife, transport, government, recreation

Output Schema

TableJSON Schema

Name	Required	Description
`items`	No
`geojson`	No
`metrics`	No
`summary`	No	Map of scalar facts the LLM should surface verbatim
`display_hint`	No

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, and open-world behavior. The description adds the categorical and proximity-based nature of the search, and how it differs from `explore`, which is useful context beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose and examples. The second sentence provides sharp usage guidance and an explicit alternative. There is zero redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema, detailed input schema, and annotations, the description covers the essential context. It explicitly distinguishes from the most similar sibling (`explore`) and provides category examples, making it sufficiently complete for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with detailed parameter descriptions and defaults. The description adds practical query examples but doesn't introduce new parameter semantics beyond what the schema provides, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'CATEGORY-specific POI search near a point', which clearly identifies the tool's action, resource, and scope. Concrete examples like 'gas stations, truck stops, restaurants' and the explicit contrast with `explore` distinguish it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit when-to-use guidance: 'Use this when the user has a specific TYPE of place in mind' and for broader discovery, 'use `explore` instead.' This clearly names the alternative and sets a crisp boundary, which is ideal for agent selection.

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

All ThinAir Geo tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose. Overlapping tools (geocode vs geocode_structured, explore vs search_places, map_match vs trace_attributes) are explicitly differentiated in their descriptions, with cross-references guiding correct selection. No two tools appear to do the same thing.

Naming Consistency4/5

Most tools follow a predictable verb_noun pattern (geocode, reverse_geocode, batch_geocode, search_places, resolve_intersection), but there are minor deviations: some tools use noun-only names (directions, traffic, weather) and a couple use noun_verb order (place_get, geofence_contains). This creates slight inconsistency but remains readable.

Tool Count4/5

At 19 tools, the set is slightly heavy but each tool earns its place by covering a distinct geospatial function. The breadth spans geocoding, routing, places, telematics, geofencing, traffic, weather, and account management, making the count reasonable for a comprehensive geo API.

Completeness5/5

The tool surface is remarkably complete for a geospatial server: forward, reverse, batch, structured, and intersection geocoding; routing, matrix, and isochrones; place search, exploration, and ID lookup; map matching, trace attributes, and point snapping; plus geofencing, traffic, weather, and quota management. No critical gaps or dead ends apparent.

Resources

Need Help?