export_spec

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive). The description adds the 'open diagram' state dependency and 'canonical schema' nuance, but does not disclose behavior such as error handling for missing/invalid diagram references or whether the export returns a string vs. triggers a file download. Since annotations cover the main safety aspects, this is adequate but not rich.

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-constructed sentence that packs the essential information (verb, resource, output formats) with no filler. It is immediately understandable and front-loaded with the action.

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?

The tool is relatively simple with only two parameters and an output schema, so the description covers the core purpose and the main prerequisite. The presence of an output schema means return values are structured, reducing the need for format details. Missing is a brief note on how to identify an 'open diagram' or error behavior, but overall the description is complete enough for correct selection and invocation.

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 descriptions cover 0% of parameters, so the description must compensate. It indirectly explains the 'format' parameter by mentioning 'YAML or JSON', and 'diagram' by referencing 'an open diagram'. However, it doesn't specify how to reference the diagram (name, ID), what the default format is, or any value constraints beyond the enum. The compensation is partial.

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 'Export' and the resource 'an open diagram's canonical schema', with output formats 'YAML or JSON'. This distinguishes it well from siblings like save_diagram (which saves diagram state) or describe_diagram (which likely returns a human-readable summary).

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 phrase 'an open diagram' implies the prerequisite that a diagram must be currently open, providing clear context for when this tool is applicable. It doesn't explicitly mention alternatives or when not to use it, but the description's clarity makes the use case obvious compared to sibling tools.

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