Maps by DeltaBreen

pois_nearby

Read-only

Landmarks and points of interest (museums, castles, beaches, national parks, cathedrals, monuments, …) near a point or a named place, closest first, each with coordinates, category and an image where one exists. Give lng+lat or a place name (place is resolved internally, uncounted). Counts one lookup against the workspace's monthly searches, on every plan; past the plan it returns searches_exhausted and nothing is charged.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pois_nearby"
  }
}

Input Schema

Name	Required	Description
`lat`	No	Latitude of the centre, -90 to 90.
`lng`	No	Longitude of the centre, -180 to 180. Give lng+lat, OR place, not both.
`limit`	No	How many to return, 1 to 50, closest first. Default 20.
`place`	No	A place name to centre on instead of coordinates (resolved internally, uncounted), e.g. "Dublin".
`key_id`	No	The map key (uuid from list_keys) to count the lookup against. Default: the workspace's first active secret key, else its first publishable one.
`category`	No	Limit to one category (museum, castle, beach, national_park, cathedral, monument, …). Default: all.
`radius_m`	No	Search radius in metres, 100 to 50000. Default 2000.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations only say readOnly/openWorld, but the description goes further: it discloses the billing unit ('counts one lookup against the workspace's monthly searches, on every plan'), the exact failure mode ('searches_exhausted and nothing is charged'), the result ordering, and the returned fields. That is the kind of quota/cost context an agent needs before calling.

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 dense sentences: resource and ordering first, then the input contract, then the cost model. No filler and the most decision-relevant facts are front-loaded.

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?

Covers ordering, returned fields, defaults via schema, and full cost/failure behaviour, so an agent can call it and interpret the result without an output schema. Minor gaps: no indication of what happens if both coordinates and place are supplied, or whether results can come back empty.

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 100%, so the baseline is 3; the description earns above that by explaining that place is resolved internally and is uncounted, and by restating the lng+lat vs place exclusivity as a behavioural rule. It doesn't add anything for limit, radius_m, category or key_id beyond the schema.

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?

Specific verb+resource with concrete category examples (museums, castles, beaches, national parks), plus the proximity semantics and 'closest first' ordering. It implicitly separates itself from search_pois/poi_details by being proximity-based, but never names a sibling to make the split explicit.

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?

Gives the input contract ('Give lng+lat or a place name') and the fallback behaviour when quota is exhausted, which is useful usage context. However, it never states when to use this over search_pois (name-based) or poi_details (single POI), so sibling selection is only inferable.

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

All Maps by DeltaBreen tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?