create_process

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

With no annotations, the description carries the full burden and handles it well: file writing, preview-only mode when output_path is empty, overwrite replacement semantics, large return_xml payloads, and formatting/layout behavior are all disclosed.

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 main purpose is front-loaded, followed by compact behavior notes and a terse argument list. Every sentence adds operational value without filler.

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 complex spec-object tool with no annotations, this is unusually complete: input format source, output behavior, preview mode, overwrite safety, response-size tradeoff, and audit result are all covered. The output schema handles the remaining return-shape details.

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%, and the description compensates fully: spec is tied to get_spec_reference(), output_path explains preview behavior, overwrite explains replacement, and return_xml warns about large responses. This adds far more meaning than the bare schema properties.

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 opens with a specific action and artifact: 'Generate a BPMN 2.0 diagram from a process specification and write it as a .bpmn file.' It further differentiates from siblings by naming Bizagi Modeler import, making it distinct from list/update/read/validate/render tools.

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?

It gives clear operational context: call get_spec_reference() for the spec format and leave output_path empty to preview. However, it never explicitly states when to choose this tool over siblings like render_preview, validate_process, or bizagi_import_bpmn, so alternatives are left to inference.

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