create_bpmn_diagram

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

Annotations already declare the write/open-world nature, but the description adds substantial context beyond them: it returns a diagram ID for reuse, warns that forcing autoLayout:true may reposition elements and disturb boundary event placement, notes that xml/filePath imports start with an empty undo/redo history, and explains lint-feedback suppression semantics. This is exactly the kind of side-effect disclosure a mutation tool needs.

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?

Front-loads the three creation modes before the return value and caveats, so the primary decision is answered first. It is a dense single block of prose, though; the autoLayout warning and workflow tips could be more scannable, keeping it just shy of a 5.

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?

For a 9-parameter, zero-required creation tool with no output schema, the description covers the return value (diagram ID), the mode selection logic, and the major side-effect caveat. It is nearly complete, though it does not explain default naming or what a blank diagram contains.

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 coverage is 100%, so the baseline is 3 and the schema carries most parameter documentation. The description still adds meaning on top: it clarifies the mutual exclusivity of cloneFrom vs xml/filePath, the auto-detection rule for autoLayout when omitted, and that hintLevel overrides draftMode. Marginal but real added value over the schema.

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?

States a specific verb (create) and resource (BPMN diagram) and immediately enumerates the three distinct modes: blank, cloned via cloneFrom, or imported from xml/filePath. An agent can tell this apart from add_bpmn_elements, create_bpmn_participant, and the other create-adjacent siblings without opening any schema.

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?

Explicitly routes between modes: cloneFrom is ignored-alternative to xml/filePath, autoLayout is only meaningful with xml/filePath, and draftMode vs hintLevel precedence is stated. It also names the concrete workflow (combine with export_bpmn filePath for open→edit→save) and the condition for each path, leaving little to inference.

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