Skip to main content
Glama

render_static

Read-only

A PNG of a place: centre, zoom, size and a look, with optional markers, lines and areas drawn on top; leave out the centre and zoom to fit the picture to what is drawn. To picture a route, pass the directions tool's geometry as a path "color,width,enc6:" with pins at its ends. Studio plan and above. Returns the image, a signed URL that works anywhere (email, chat, a page) with no key in it, and the plain URL for use with a publishable key on a site. A given picture (overlays included) counts one static map image against the workspace's monthly allowance once a week, however often it is viewed. Past the allowance the tool returns images_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": "render_static"
  }
}

Input Schema

NameRequiredDescriptionDefault
zoomNo0 (the world) to 20 (a building). Streets read well at 14 to 16. Required with a centre.
pathsNoLines, each "color,width,lng,lat,lng,lat,…" (up to 100 points) or "color,width,enc6:<polyline6>" for a route's geometry from the directions tool (up to 4,000 points, thinned to 500): color 3/6 hex, width 1–16. E.g. "0a84ff,4,-6.2,53.3,-6.3,53.4".
pitchNoTilt in degrees, 0 to 60.
styleNoA built-in look (meadow, midnight, neon, vintage, blueprint, sakura), a published style id, id@version, or one of the workspace's style URLs. Default meadow.
widthNoPixels, 1 to 1280. Default 600.
centerNo[longitude, latitude] of the map's centre. Omit it (and zoom) to fit the picture to the markers, paths and areas.
heightNoPixels, 1 to 1280. Default 400.
key_idNoThe map key (uuid from list_keys) to count the image against and sign the URL with. Default: the workspace's first active secret key, else its first publishable one.
retinaNoRender at 2x for high-density screens; the image is twice the pixels.
bearingNoRotation in degrees, 0 to 360.
markersNoPins and dots to drop on the map, each "lng,lat[,icon][,color][,label]": icon is pin (default), pin-sm or dot; color is 3/6 hex without '#'; label is one or two letters or digits. E.g. "-6.26,53.35,pin,e11d48,A". Up to 20.
languageNoLabel language, e.g. "en", "de", "ja", "zh-Hans" (41 in all); omit for local names.
polygonsNoFilled areas, each "fill,stroke,lng,lat,lng,lat,…" (three or more points). E.g. "e11d48,111111,-6.2,53.3,-6.3,53.3,-6.3,53.4".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already mark this readOnly/openWorld=false, and the description goes well beyond by disclosing the return shape (the image, a signed URL usable anywhere without a key, and a plain publishable-key URL), the billing model (one image counted per week per distinct picture, regardless of views), the plan requirement, and the images_exhausted error with no charge. That is exactly the kind of cost/side-effect 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.

Conciseness4/5

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

It is front-loaded: what the tool produces and its key levers come first, then the route-reuse tip, then returns/quota. The final sentence about weekly counting and images_exhausted is long but is genuinely load-bearing for the agent. It could be split into shorter sentences for scannability, but no sentence is wasted.

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 13-parameter, all-optional renderer with no output schema, the description covers returns, key/signing behaviour, plan requirement, quota accounting and the images_exhausted failure. It doesn't mention other error modes or how the image is encoded in the response, which are minor gaps given the schema already covers all 13 parameters.

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 adds real value by describing the fit-to-overlay behaviour when centre/zoom are omitted and by explaining the path encoding reuse of directions geometry. Beyond those interactions and the style default, most parameter detail (ranges, formats, defaults) lives in the already-complete 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?

The description opens by naming the exact artifact ('A PNG of a place') and enumerates the levers (centre, zoom, size, look) plus overlays (markers, lines, areas), so the agent can immediately tell this returns an image rather than map code or a snippet. It stops short of naming a sibling explicitly (e.g. snippet, map_code), so the differentiation is inferred rather than stated.

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?

It gives clear context for two situations: when to omit centre/zoom to fit overlays, and how to chain from the directions tool to picture a route ('pass the directions tool's geometry as a path ... with pins at its ends'). It states a prerequisite ('Studio plan and above') but offers no when-not-to-use or 'use X instead' exclusion against adjacent tools.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources