Apply targeted edits to an existing Draw.io diagram by adding or removing nodes, rewiring connections, grouping elements into containers, or highlighting paths.
Surgically patch an existing diagram: add/delete/update nodes, rewire edges, group into containers, or highlight paths.
| Name | Required | Description | Default |
|---|---|---|---|
| operations | Yes | ||
| drawio_path | Yes | ||
| output_path | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v2.0.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden. It lists the operation types (add/delete/update nodes, rewire edges, group, highlight) and implies surgical modification, but does not disclose whether it modifies in place or requires an existing file, side effects, error handling, or the nature of the return value. This is a moderate disclosure but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, densely packed sentence that conveys the purpose and scope efficiently. It is front-loaded with the primary action and lists specific operation types, avoiding unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having an output schema, the description does not explain the operation format, the relationship between input and output paths, or the expected response. For a tool with a complex operations array, this is insufficient for an agent to construct valid calls. The description lacks critical parameter details and behavioral constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It mentions 'operations' conceptually (listing possible actions) but does not explain the structure of the operations array, the meaning of drawio_path and output_path, or how they interact. Only minimal semantic value is added beyond the parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a strong verb ('patch') and specifies the resource (existing diagram) and the scope of modifications (add/delete/update nodes, rewire edges, group, highlight). It clearly differentiates from siblings like create_diagram (new diagram) and generate_* tools (from scratch), and from read-only analyze_diagram.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this is for modifying an existing diagram, but does not explicitly state when to choose it over alternatives (e.g., 'use create_diagram for new diagrams' or 'use analyze_diagram for inspection'). The purpose is clear enough for an agent to infer, but no explicit when/why-not guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.