Skip to main content
Glama
Sign In
Pavo 官网 MCP

Pavo 官网 MCP

by congliu1851-ui
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

更新节点和提示词

pavo_update_node
Idempotent

Update a canvas node by deep-merging supplied parameters, preserving unknown fields and media, replacing only prompt text, and rejecting conflicting field overwrites.

Instructions

保留未知字段并深合并指定参数。prompt只替换文字片段，保留skill及媒体。版本冲突若同字段已改则拒绝覆盖。

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": {
      "project_uuid": "<project_uuid>",
      "canvas_uuid": "<canvas_uuid>",
      "node_key": "<node_key>",
      "operation_id": "<operation_id>"
    },
    "name": "pavo_update_node"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
modelNo
paramsNo
promptNo
dry_runNo
node_keyYes
data_patchNo
canvas_uuidYes
operation_idYes
project_uuidYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

B3.1/5.0
Behavior4/5

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

Beyond the annotations (non-readOnly, non-destructive, idempotent, openWorld) it discloses genuinely useful behavior: unknown fields are preserved, params are deep-merged, prompt edits only replace the text fragment while keeping skill and media, and same-field version conflicts are refused rather than clobbered. It stops short of explaining the dry_run path or how the conflict is surfaced. Nothing conflicts with destructiveHint=false.

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 short, front-loaded sentences with no filler; the highest-risk semantic (merge vs replace) comes first. Slightly telegraphic, but every sentence earns its place.

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?

An output schema exists, so return values need no explanation. However, for a 10-param mutation with zero schema documentation, the absence of any note on dry_run, operation_id, or conflict-recovery behavior leaves real gaps an agent would need before calling it.

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 0% for 10 parameters, so the description carries the burden. It does explain the two structurally risky ones (params/data_patch deep-merge, prompt partial replacement), but leaves dry_run, operation_id (presumably an idempotency key), node_key, and the UUID scoping parameters entirely unaddressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description never states the action outright ("update node"); it only describes merge/preservation semantics. Combined with the name and title the intent is inferable, but there is no differentiation from siblings such as pavo_create_node, pavo_apply_canvas, or pavo_get_node.

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

Usage Guidelines2/5

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

No guidance on when to choose this over pavo_create_node or pavo_apply_canvas, and no preconditions (e.g., needing a prior pavo_get_node read for the version/conflict check). The dry_run flag, which is the obvious safe-preview path, is never mentioned.

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