Skip to main content
Glama

Tomtom

by io.github.pipeworx-io

Search Poi

search_poi
Read-onlyIdempotent

Search for points of interest (POIs) — businesses, landmarks, restaurants, gas stations, etc. — by name or category, optionally near a lat/lon center within a radius. Returns name, category, address, coordinates, phone, url, and distance. Example: search_poi({ query: "coffee", lat: 40.748, lon: -73.985, radius: 1000 })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latNoOptional latitude of the search center to bias/limit results
lonNoOptional longitude of the search center to bias/limit results
limitNoMaximum number of results to return (default 10)
queryYesPOI search term, e.g. "coffee", "pizza", "gas station", "Starbucks"
radiusNoOptional search radius in meters (only used when lat/lon are provided)
_apiKeyNoOptional — your own TomTom API key for higher limits; omit to use the shared Pipeworx key.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "_apiKey": "your-tomtom-api-key",
+    "lat": 40.748,
+    "lon": -73.985,
+    "query": "coffee",
+    "radius": 1000
+  },
+  {
+    "_apiKey": "your-tomtom-api-key",
+    "limit": 5,
+    "query": "gas station"
+  }
+]
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. The description adds return field details but no additional behavioral context (e.g., rate limits, data freshness). With annotations present, the description contributes some value but not significant beyond structured fields.

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?

The description is a single sentence front-loaded with purpose, followed by parameters and return fields, plus a compact example. Every word is useful, no redundancy, and it is appropriately sized for quick comprehension.

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

Completeness5/5

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

Given no output schema, the description lists all key return fields (name, category, address, coordinates, phone, url, distance) and provides an explicit example. All six parameters are covered in schema and description, making the tool's functionality complete for an agent.

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 coverage is 100% with each parameter described. The description reinforces parameter usage via example and mentions 'by name or category' and 'near a lat/lon center', but does not add novel semantic information beyond the schema. Baseline 3 is appropriate.

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 clearly states 'Search for points of interest (POIs) ... by name or category', specifying the verb, resource, and scope. It lists return fields and provides an example, making the tool's purpose unambiguous and distinct from sibling tools like geocode or route.

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

Usage Guidelines3/5

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

The description implies usage for POI searches but does not explicitly state when not to use this tool or mention alternatives. No exclusions or comparison to siblings like search_within or geocode are provided, limiting guidance for agent decision-making.

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

All Tomtom toolsInspect
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

A3.9/5.0
Disambiguation3/5

Several tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta (currently identical behavior), and ask_pipeworx_grounded are variants of the same router, and the six polymarket_* tools plus bet_research all operate in the same prediction-market space. The extremely detailed descriptions help an agent differentiate, but misselection risk remains real.

Naming Consistency4/5

Snake_case is used consistently and most tools follow a verb_noun pattern (resolve_entity, validate_claim, discover_tools), with predictable polymarket_ and pipeworx_ family prefixes. Minor deviations exist — entity_profile and recent_alerts are noun/adjective phrases, generate_llms_txt embeds a file extension, and single-word verbs (remember, route, geocode) break the strict pattern — but overall naming is coherent.

Tool Count2/5

At 35 tools, the server exceeds the comfortable range and bundles many unrelated domains: data lookup, prediction markets, geocoding/navigation, memory, subscriptions, AI visibility, npm scanning, and llms.txt generation. While every tool has a distinct purpose, the surface is heavy and would benefit from splitting into focused servers.

Completeness4/5

Each major cluster has strong lifecycle coverage: data lookup (router, grounded mode, deep research, discovery), company research (resolve, profile, compare, changes), prediction markets (research, arb, edges, fill risk, cross-venue spread), memory (remember/recall/forget), and subscriptions (subscribe/list/unsubscribe/alerts). Minor gaps exist — no direct Polymarket order placement and no explicit tool for fetching pipeworx:// URIs (left to resources) — but agents can accomplish the stated purposes.

Resources