Skip to main content
Glama

List recent canvas changes

list_recent_canvas_changes
Read-onlyIdempotent

List recent semantic canvas changes with actor, scope, targets, timestamps, and exact/inferred grouping evidence. Each item names its page (canvasPageName) and its frame targets by name, kind and state (active, or gone when the frame no longer resolves). A frame delete, move or create arrives as operationKind: 'layout' with a page-root target (frameId: null), because it is one opaque update to the page's layout doc; detail: 'patch' attaches a layout delta that names the frames added and removed. Defaults to this credential's OWN changes — the result echoes actors so an empty page-scoped read is legible as 'none of yours', not 'nothing happened' — and actors: 'all' (with scope: { branchId }; projectId is derived) is how to see the human's edits. Scope: project:read.

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": "list_recent_canvas_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax changes to return. Default 20.
scopeNoExplicit branch to read (`{ branchId }` is enough). Required when `actors: 'all'`; omit for your own changes across every branch.
actorsNoWhose changes to list. Default `self` — ONLY this credential's writes, so a human's edits and deletes on the same page are excluded until you pass `all` (which needs an explicit `scope`). The result echoes which one applied.
cursorNoContinuation cursor from a previous call's `nextCursor`. Omit for page one.
detailNoDefault `summary`. `patch` adds the diff for each change — much larger — and, for page-root (`layout`) changes, a structured `layout` delta naming the frames added or deleted; that is the only way a deleted frame's id is reported.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds substantial context beyond them: default self-only filtering, echoed actors, empty-read interpretation, required project:read scope, and the special opaque layout-update semantics for frame deletes/moves/creates. It also explains that `detail: 'patch'` is the only way a deleted frame's id is reported.

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 description is dense and long, but it is front-loaded with the core purpose and then presents the important behavioral details in a logical order. Some sentences are packed with multiple clauses, but nearly every detail earns its place given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex read tool without an output schema, the description is complete enough: it explains the returned fields, page and frame target shape, layout-operation special cases, actor echoing, and the required auth scope. An agent has the necessary context to call it correctly and interpret unusual results.

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 schema already documents each parameter, but the description adds cross-parameter meaning: `actors: 'all'` needs an explicit scope, `projectId` is derived from `branchId`, and `detail: 'patch'` changes the shape of returned data for layout changes. It does not add much about `limit` or `cursor`, but those are well covered by the schema.

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?

The description opens with a specific verb and resource: 'List recent semantic canvas changes' and enumerates the returned evidence: actor, scope, targets, timestamps, and grouping evidence. This clearly distinguishes the tool from sibling frame/page/state readers by focusing on change history rather than current canvas structure.

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 usage context: default reads only this credential's own changes, while `actors: 'all'` with `scope: { branchId }` is required to see human edits. It does not explicitly name alternative sibling tools or state when not to use this tool, but the conditions for key parameter choices are well explained.

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