Skip to main content
Glama

update_map

Change a dashboard map: its name, settings (named one by one, the rest kept), pins (replace them all, add some, or remove some by id), a pasted spreadsheet (csv, replacing the pins), lines and areas, category colours and symbols, and sharing it as a page of its own. Every save keeps the one it replaced, so the dashboard can bring it back. Sites showing the map pick up the change within a minute. Owner or admin.

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": {
      "map_id": "<map_id>"
    },
    "name": "update_map"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvNoA spreadsheet as CSV with a header row, replacing the map's pins (see create_map).
nameNo
pinsNoEvery pin, replacing the map's (see create_map for the fields).
glyphsNoSymbols by category name, replacing the map's.
map_idYesThe map's id (uuid), from list_maps or create_map.
publicNoShare the map as a page of its own (a link and a QR code for any site, Google Sites or Notion included), or stop sharing it.
shapesNoEvery line and area, replacing the map's (see create_map).
add_pinsNoPins to add to the map's.
settingsNoSettings to change by name; the rest stay as they are (see create_map for the names).
categoriesNoColours by category name, replacing the map's.
frame_sitesNoThe sites that may show that page in a frame, e.g. ["sites.google.com", "*.example.com"].
remove_pinsNoThe ids of pins to take off the map.
frame_anywhereNoLet any site show the page in a frame.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial context beyond annotations: prior versions are retained so the dashboard can restore them, changes propagate to embedding sites within a minute, and owner/admin authorization is required. These disclosures (undoability, latency, auth) are exactly what annotations leave unanswered, and none contradict destructiveHint=false.

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?

Front-loaded with the verb and a dense but purposeful field enumeration, followed by three short behavioral sentences. The first sentence is long and comma-chained, but every clause carries information not duplicated in the schema.

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 all parameter groups of a 13-parameter mutation tool, plus versioning, propagation, and permissions, with no output schema needing explanation. It stops short of stating precedence when pins, add_pins, and csv are combined, which is the one gap for a tool this flexible.

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 92%, so baseline is a 3, but the description adds real semantics: it distinguishes replace-all pins, add_pins, and remove_pins by id, and notes that csv supersedes pins and that settings merge rather than replace. Minor ambiguity remains when multiple pin parameters are supplied together.

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?

Opens with a specific verb and resource — 'Change a dashboard map' — then enumerates the exact aspects that can be changed (name, settings, pins, csv, shapes, categories, sharing). An agent can tell this apart from create_map or update_style without opening a schema.

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?

Clear operational context: partial-update semantics are spelled out ('settings named one by one, the rest kept') and the permission gate is stated ('Owner or admin'). It does not explicitly name create_map as the alternative for new maps, so it falls short of a 5.

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