Draw.io MCP Server

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

No annotations are provided, so the description carries the full burden. It discloses that it returns 'the shape and also the category it belongs', adding useful context beyond the basic retrieval action. However, it doesn't cover other behavioral traits like error handling (e.g., if the shape doesn't exist), performance aspects, or whether it's a read-only operation (implied by 'Retrieve' but not explicit). The description doesn't contradict any annotations, as none are given.

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?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose and return value. It is front-loaded with the main action ('Retrieve a specific shape by its name'), followed by context ('from all available shapes in the diagram's library') and output details ('It returns the shape and also the category it belongs'). There is no wasted verbiage, making it highly concise and clear.

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?

Given the tool's low complexity (one parameter, no output schema, no annotations), the description is adequate but has gaps. It explains what the tool does and what it returns, which is sufficient for basic understanding. However, without annotations or output schema, it lacks details on error cases, return format (e.g., structure of the shape object), or how it interacts with sibling tools. This makes it minimally viable but not fully comprehensive for an agent's needs.

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?

The input schema has 100% description coverage, with the parameter 'shape_name' documented as 'Name of the shape to retrieve from the shape library of the current diagram.' The description adds that it retrieves 'by its name from all available shapes', reinforcing the parameter's purpose but not providing additional syntax, format details, or constraints beyond what the schema already states. With high schema coverage, the baseline is 3, and the description meets this without significant extra value.

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 clearly states the verb ('Retrieve') and resource ('a specific shape by its name'), specifying it comes from 'all available shapes in the diagram's library'. It distinguishes from siblings like 'get-shapes-in-category' (which retrieves multiple shapes) and 'get-shape-categories' (which retrieves categories). However, it doesn't explicitly differentiate from 'get-selected-cell' (which retrieves a selected cell rather than a shape by name), leaving room for minor ambiguity.

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 usage by stating it retrieves 'by its name from all available shapes', suggesting it's for fetching a single shape when the name is known. However, it lacks explicit guidance on when to use this versus alternatives like 'get-shapes-in-category' (for shapes in a category) or 'get-selected-cell' (for a selected cell), and doesn't mention prerequisites or exclusions, such as whether the shape must exist in the library.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.