Skip to main content
Glama

ai_modeling_canvas_answer_plan

Read-only

Prepare exact Canvas selection or confirmation card answers—including grouped questions, Other, skip, and confirmed parts—after checking turn, session, and node assets; does not submit.

Instructions

Prepare an exact Canvas selection or confirmation card answer, including grouped questions, Other, skip and confirmed parts. Checks turn/session/Canvas and selected node assets; does not submit or accept variable billing. Any answer, including Skip, may continue paid creation; use turn-cancel to cancel.

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>",
      "turnId": "<turnId>",
      "cardMessageId": "<cardMessageId>"
    },
    "name": "ai_modeling_canvas_answer_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNocontinue
turnIdYes
canvasIdYes
otherTextNoFree text for a single selection or confirmation card.
otherTextsNoFor grouped questions, map question IDs to text, for example {"q1":"a red panda"}; keys are not option IDs such as q1:__other__.
cardMessageIdYes
confirmedPartsNo
selectedOptionIdsNoActual option IDs from the card, such as q1:__other__; do not use question IDs here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, so the safety profile is covered, yet the description adds real context beyond them: pre-flight validation of turn/session/Canvas/selected node assets, the fact that it does not accept variable billing, and the critical consequence that any answer, including Skip, may continue paid creation. That billing warning is exactly the kind of behavioral fact an agent cannot get from structured fields. It does not describe what the prepared answer looks like or how it is consumed.

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 dense sentences with the core action front-loaded, followed by scope of validation and then the billing risk. Nothing is padded, though 'does not submit or accept variable billing' is a compressed phrase that takes a second read to parse.

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

Completeness3/5

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

For an 8-parameter tool with a nested object, no output schema, and 38% description coverage, the description covers the highest-stakes concern (paid creation continues even on Skip) but leaves two gaps: what the prepared answer actually returns and how the agent should then submit it, and the identity/format semantics of the required IDs. Adequate but not complete for the complexity.

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 coverage is only 38% across 8 parameters, including a nested object, so the description carries more burden than usual. It does map conceptually onto several parameters (grouped questions/otherTexts, Other/otherText, skip/action, confirmed parts/confirmedParts), which adds orientation value, but the three required identifiers (canvasId, turnId, cardMessageId) and the option-ID-versus-question-ID rule are left entirely to 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?

The description uses a specific verb ('Prepare') on a specific resource ('Canvas selection or confirmation card answer') and enumerates the card shapes it handles: grouped questions, Other, skip, confirmed parts. It is clearly distinguishable from sibling execution tools like ai_modeling_canvas_continue because it explicitly says it does not submit. It stops short of stating outright that this is a plan-only step that must be followed by a submit call, which would have made the distinction airtight.

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?

It gives a genuine when-not ('use turn-cancel to cancel') and warns that it does not submit, which implies another tool must perform submission. However, that submitting sibling is never named, nor is there guidance on when to choose this over the other *_plan siblings. Usage is therefore implied rather than spelled out.

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