Skip to main content
Glama

ai_modeling_canvas_lab_inputs

Read-only

Resolve a Lab node's new upstream assets and explicit attachments while excluding inputs already used in Lab history, returning missing inputs without starting a job.

Instructions

Resolve a Lab node’s new upstream assets plus explicit attachments, excluding inputs already used in observed Lab history. Returns missing inputs without starting a job.

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>"
    },
    "name": "ai_modeling_canvas_lab_inputs"
  }
}

Input Schema

NameRequiredDescriptionDefault
nodeIdYes
assetIdsNoExplicit attachments appended after new upstream assets; these are not removed by history deduplication.
canvasIdYes
revisionNo
historyLimitNoOptional bound for the Lab history query; omitted uses the same service default as the webpage.

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, so the safety profile is covered; the description still adds real behavioral detail by explaining the deduplication rule (excludes inputs already used in observed Lab history) and that resolution does not trigger a job. It does not describe pagination, error modes, or what 'observed history' means operationally, which keeps it below 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly packed sentences with the core behavior front-loaded and the non-obvious side effect ('without starting a job') placed at the end as a qualifier. No filler or restated name.

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 read-only resolution tool with no output schema, the two sentences cover what is resolved, what is excluded, and what is returned ('missing inputs') without triggering work. The one omission is the shape of the returned missing-inputs list and the undocumented revision parameter, but the annotations and schema already establish the safety and parameter contract.

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 40%, with descriptions only on assetIds and historyLimit, so the description must carry the rest. It reinforces the assetIds semantics ('explicit attachments') and hints that history is queried, but says nothing about canvasId, nodeId, or especially the undocumented revision string parameter. Partial compensation, not a fix for the coverage gap.

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 gives a specific verb and resource: resolve a Lab node's upstream assets plus explicit attachments, deduplicated against Lab history, returning missing inputs without starting a job. That is materially different from sibling tools like ai_modeling_canvas_lab_plan or ai_modeling_canvas_node_assets, though it never names those siblings explicitly. The jargon ('Resolve', 'observed Lab history') leaves the exact computation slightly abstract.

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?

'Without starting a job' implies the pre-flight use case and implicitly contrasts with the run/job tools, but the agent must infer that. There is no explicit 'use this when...' clause and no named alternative to select against, so guidance is only implied.

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