Skip to main content
Glama
Sign In
duddy

duddy

by qu15501267889-sketch
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

duddy_apply_step

Executes one approved step at a time from a ComfyUI change plan, reporting created nodes, connections, and remaining steps so you can verify progress before continuing.

Instructions

【第二步·逐个动手】执行计划的下一步，一次只走一步。

前置条件：用户已经在 ComfyUI 弹窗里点了「同意」，plan.state == approved/applying。 如果返回 403 not_approved，说明用户还没批准。此时你必须停下来，告诉用户「请在弹出的窗口里点同意」，然后等待。 严禁尝试其它方式绕过（直接 POST /prompt、写 workflow 文件、批量推送都不行）。

返回里会告诉你这一步建了/连了什么、真实 node_id、剩余步数。把结果用一句话回报给用户，再决定要不要继续下一步。

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": {
      "plan_id": "<plan_id>"
    },
    "name": "duddy_apply_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
plan_idYes
expected_indexNo你期望执行的步骤序号（从 0 开始）。填了可以防止跳步，建议总填

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose key behavior: one-step-at-a-time execution, a specific failure mode and HTTP code (403 not_approved) with the required agent response, and the shape of the returned result (what node was created/connected, real node_id, remaining step count). It does not state whether applied steps are reversible or what happens if a step fails mid-plan, so it stops short of full behavioral disclosure.

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?

Front-loaded with the action, then a clearly separated prerequisites block and an error-handling block, which is easy to scan. Some wording is redundant (restating that the result should be reported to the user in one sentence), but overall it is proportionate to the risk of the tool.

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 mutation tool with no annotations and no output schema, the description covers prerequisites, error behavior, the return payload, and the agent's follow-up obligation. The missing piece is how to obtain plan_id and whether calling a step twice is safe, which matters given the sequencing semantics.

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

Parameters2/5

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

Schema coverage is only 50%: plan_id has no schema description at all, and expected_index is documented only in the schema (as an anti-skip guard). The description never explains where plan_id comes from or when to pass expected_index, so it does not compensate 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 opens with a specific verb+resource: execute the next step of a plan, one step at a time, and labels itself as 'step 2' in a sequence, so an agent can distinguish it from planning/status siblings such as duddy_plan_status or duddy_precheck_plan. It falls short of a 5 because it never names those siblings explicitly as the tools to use for checking prerequisites.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use (plan.state == approved/applying and the user has clicked approve in the ComfyUI dialog), explicit when-not (403 not_approved means stop and tell the user to approve), and explicit forbidden alternatives (no direct POST /prompt, no writing workflow files, no batch pushing). This is unusually complete routing guidance.

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