here-hgv-mcp

HERE search places (discover / browse)

here_search_places

Read-only

Find fuel stations, truck stops, depots, services, and restaurants around a coordinate using free-text or HERE category searches, with distance-ranked results for HGV route planning.

Instructions

Find places around a coordinate — fuel stations, truck stops, depots, services, restaurants, etc. Free-text search uses HERE Discover v7 ("q"). If you pass "categories" it uses HERE Browse v7 with HERE Places category IDs (e.g. "700-7600-0116" for petrol stations) and "name" filtering. Always ranked by importance/distance from the supplied "at" point; radiusM is a hard circle filter. UK default: 2 km radius, en-GB names. HGV tip: combine with here_route to check whether the access is suitable for a large vehicle — place categories alone do not encode HGV access. openNow is best-effort: HERE GS7 returns no opening-hours data, so when it cannot be determined the response carries openNowApplied=false plus a warning and unfiltered items.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "at": "<at>"
    },
    "name": "here_search_places"
  }
}

Input Schema

Name	Required	Description
`q`	No	Free-text query, e.g. "petrol station", "truck stop", "M6 services". Required unless categories is supplied.
`at`	Yes	Search centre as "lat,lng", e.g. "53.4808,-2.2426". Required — HERE Discover/Browse rank by distance from it.
`lang`	No	BCP-47 language for names/addresses, default en-GB.
`limit`	No	Maximum places to return (default 10).
`offset`	No	Pagination offset (0-99).
`openNow`	No	Best-effort filter to currently-open places (see tool description).
`radiusM`	No	Circle radius in metres around "at" (50-50000, default 2000).
`categories`	No	HERE Places category IDs (Browse). A "!" prefix excludes a category. Example: ["700-7600-0116"] for petrol stations.
`mobilityMode`	No	Improves result relevance for the travel mode; "truck" biases towards HGV-accessible places.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only declare readOnly and openWorld, but the description adds real behavioral depth: ranking is by importance/distance from 'at', radiusM is a hard circle filter, UK defaults of 2 km and en-GB apply, and two different HERE backends are used depending on the parameters supplied. It also discloses a known limitation honestly — openNow is best-effort, GS7 returns no hours, and the response falls back to openNowApplied=false with a warning and unfiltered items.

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?

Front-loads the core action, then layers mode selection, ranking/radius semantics, regional defaults, and the openNow caveat in a tight sequence. Every sentence carries information an agent would otherwise have to guess, and nothing is repeated from the schema verbatim.

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?

For a 9-parameter read-only search with no output schema, the description covers the decisions that matter: which parameters select which backend, how results are ordered and bounded, regional defaults, and one response-shape detail (openNowApplied=false plus warning). A brief note on pagination or result-object shape would close the remaining gap.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline would be 3; the description earns above that by explaining the interaction between 'q' and 'categories' (mutually selecting Discover vs Browse), the HERE category ID form, and the reliability semantics of openNow that the schema only gestures at. It does not elaborate on limit/offset pagination behavior beyond what the schema states.

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

Purpose4/5

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

Opens with a specific verb and resource ('Find places around a coordinate') plus concrete example categories and the coordinate-scoped search centre, so the core action is unambiguous. It stops short of explicitly differentiating itself from name-similar siblings (here_geocode, here_autosuggest), leaving the agent to infer the boundary.

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

Usage Guidelines4/5

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

Gives clear conditional routing inside the tool: free text uses Discover v7 via 'q', supplying 'categories' switches to Browse v7 with HERE category IDs. It also adds a practical cross-tool tip (pair with here_route to check HGV access) and states exclusions for what categories alone cannot tell you. It does not state when a sibling such as here_autosuggest or here_geocode should be preferred instead.

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

Deploy Server