Skip to main content
Glama

ai_modeling_canvas_lab_plan

Read-only

Prepares Lab reuse instructions from current upstream assets or an exact historical run prompt and inputs; does not submit jobs or accept billing.

Instructions

Prepare Lab reuse_instructions with all current upstream assets or run_again with an exact historical prompt and original inputs. Does not submit or accept variable billing; pass ready parameters to canvas-lab separately.

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>",
      "nodeId": "<nodeId>",
      "mode": "<mode>"
    },
    "name": "ai_modeling_canvas_lab_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
jobIdNoThe exact previous Lab job for run_again; never the latest job implicitly.
nodeIdYes
canvasIdYes
revisionNo
historyLimitNo
previousInputBindingNoA prior reuse_instructions input_binding; when supplied, unchanged inputs are not ready.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-annotated context: this tool only prepares parameters and neither submits jobs nor accepts variable billing, which tells the agent this is a non-mutating planning step whose output feeds ai_modeling_canvas_lab. It does not explain what the return payload looks like or how historyLimit/revision affect behavior.

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?

Two sentences, no filler, with the primary mode distinction front-loaded and the execution boundary trailing. The phrasing is dense and jargon-dependent ('ready parameters', 'upstream assets') but every clause carries information.

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?

With seven parameters, no output schema, and a low schema coverage, the definition leaves gaps a planning tool should close: what the prepared output contains and how revision/historyLimit scope the plan. It does cover the mode decision and the hand-off to canvas-lab, which are the highest-risk points, so it is adequate rather than complete.

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 low at 29%; only jobId and previousInputBinding carry inline descriptions. The description compensates for the most important gap by explaining the mode enum ('reuse_instructions' vs 'run_again') and reinforcing that run_again needs an exact historical prompt and original inputs. However, four parameters (canvasId, nodeId, revision, historyLimit) are left with bare types and patterns and are given no meaning here either.

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 names two concrete modes, reuse_instructions and run_again, and states what each produces (current upstream assets vs an exact historical prompt with original inputs). It also names the sibling that actually executes work (canvas-lab), so the planning-vs-submitting boundary is visible. The remaining vagueness comes from the internal jargon 'Lab reuse_instructions', which an agent must already know to interpret.

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 a clear selection rule between the two modes: reuse_instructions when reusing current upstream assets, run_again when reproducing an exact historical run from a specific job. It also states a when-not boundary ('does not submit... pass ready parameters to canvas-lab separately'). No guidance is offered on when to omit optional fields like revision, historyLimit, or previousInputBinding.

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