Skip to main content
Glama

ai_modeling_canvas_turn_plan

Read-only

Prepare a new Canvas composer message or exact failed-user retry, verifying saved node assets and READY inputs, applying saved-copy bindings, and checking message limits without saving or submitting.

Instructions

Prepare a new Canvas composer message or an exact failed-user-message retry. Preserves attachment markers/order, verifies saved node assets and READY inputs, applies proven saved-copy bindings and checks Unicode/new-composer limits. Does not upload, save, submit or accept variable billing.

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": {
      "canvasId": "<canvasId>",
      "sessionId": "<sessionId>"
    },
    "name": "ai_modeling_canvas_turn_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
actionNonew
canvasIdYes
agentModeNocontrol
sessionIdYes
attachmentsNo
copiedNodesNoPre-save copied nodes from an already completed canvas save. Requires its expectedRevision; resolves old output IDs without saving again.
sourceTurnIdNo
sourceMessageIdNoExact historical USER message ID for retry, not an assistant card ID.
expectedRevisionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces that with an explicit negative scope: no upload, save, submit, or variable billing. It also discloses internal verification behavior (asset/READY-input checks, Unicode and new-composer limit checks, saved-copy bindings), which is real context beyond the annotations. What it does not disclose is the shape of the returned plan or how it must be consumed downstream.

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?

Three sentences, front-loaded with the core purpose before the behavioral detail and the exclusions. No filler, though the phrasing is dense with internal jargon ('proven saved-copy bindings', 'READY inputs') that a first-time caller may not parse quickly.

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 read-only planning tool with no output schema, the definition covers scope, preconditions checked, and what is deliberately not done, which is the information an agent needs to call it safely. The main remaining gap is the return contract: it never says the result is a prepared plan that must then be handed to a turn/send tool, so the caller has to guess the next step.

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

Parameters3/5

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

Schema description coverage is only 20% across 10 parameters, so the description has to carry weight. It does add meaning for attachments ('preserves attachment markers/order'), for copiedNodes/nodeAssets ('verifies saved node assets', 'applies proven saved-copy bindings'), and for retry via 'exact failed-user-message retry'. It says nothing about action enum values, agentMode, expectedRevision, or the canvasId/sessionId pair, leaving roughly half the surface unexplained in both places.

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 definition uses a specific verb ('Prepare') against a specific resource ('Canvas composer message') and splits the operation into two named modes: new message or exact failed-user-message retry. That distinguishes it from a plain send/turn tool. It stops short of naming a sibling explicitly, so an agent must infer that ai_modeling_canvas_turn performs the actual submission.

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?

The opening sentence states the two triggering conditions (composing a new message, retrying a failed user message), and the closing sentence carves out clear exclusions ('Does not upload, save, submit'), which implies this is a pre-flight step before a real send. No alternative tool is named, so the boundary with ai_modeling_canvas_turn is left implicit rather than stated.

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

Deploy Server

Other Tools