Skip to main content
Glama

HERE autosuggest (typed-ahead suggestions)

here_autosuggest
Read-only

Turns partial address or place queries into ranked suggestions; defaults to Great Britain and can rank results near a latitude/longitude point for proximity.

Instructions

Turn a partial address/POI query into ranked suggestions using the HERE Autosuggest v7 API — the right tool when the user has typed only part of a name ("Manch", "Traff", "M6 Toll"). UK bias by default: without at, suggestions are restricted to a Great Britain bounding box (HERE Autosuggest does not accept a country-code filter). Pass at="lat,lng" to rank suggestions near a point (e.g. the driver's current location) instead. Suggestions include addresses, places, and query terms. Use here_geocode afterwards to resolve a chosen suggestion to coordinates if it has no position. For complete addresses or coordinates use here_geocode; for places around a point use here_search_places.

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": {
      "q": "<q>"
    },
    "name": "here_autosuggest"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesPartial free-text query, e.g. "Manch", "Trafford P", "M6 Toll".
atNoOptional "lat,lng" to rank suggestions by proximity (strongly recommended for in-cab use).
langNoBCP-47 language, default en-GB.
limitNoMaximum suggestions (default 8).
countryFocusNoISO 3166-1 alpha-3 country filter, default GBR. Use "ANY" for worldwide. Ignored when at is supplied.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds useful behavior: default Great Britain bounding box, proximity ranking via at, and returned suggestion types. However, it says HERE Autosuggest does not accept a country-code filter while the schema exposes countryFocus, so the behavioral disclosure is partly misleading.

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

Conciseness4/5

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

The definition is front-loaded and organized around purpose, default geography, at usage, returned types, and alternatives. The incorrect country-filter parenthetical adds avoidable noise, and some guidance echoes schema descriptions.

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 no output schema, the description explains that suggestions include addresses, places, and query terms, and it covers follow-up resolution and alternatives. It is not fully complete because the countryFocus interaction is described incorrectly.

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

Parameters2/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds some at-proximity context, but it misstates country filtering and does not clarify countryFocus, actively undermining parameter understanding.

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?

States a specific verb and resource ('Turn a partial address/POI query into ranked suggestions'), names the API, and explicitly distinguishes itself from here_geocode and here_search_places.

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?

Gives explicit when-to-use guidance ('typed only part of a name'), names the alternatives, and explains follow-up use of here_geocode after selecting a suggestion. It also routes complete addresses/coordinates and places-around-a-point queries to the correct sibling tools.

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