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

Goes well beyond the annotations: it discloses that the definition is statically validated before write, that error-severity findings abort creation with valid=false, created=false and returned findings, and that advisory findings are surfaced on success. Annotations only cover the safety profile (non-readonly, non-destructive, non-idempotent), so this adds real behavioral value an agent could not infer.

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 core identity and the new-vs-version distinction, then layers validation semantics and the publish shortcut. Dense but every sentence carries operational meaning; the parenthetical advisory examples add minor bulk but aid authoring.

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 nested-object mutation tool with an output schema, it covers what an agent needs: schema-fetch workflow (get_workflow_definition_schema), validation timing, failure result fields, and return shape {content_type, output}. Little is left to guess.

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; the description earns above baseline by explaining the consequence of the definition parameter (pre-write validation, failure semantics) and reinforcing the publish=true one-step behavior. It doesn't add much on slug/display_name/description beyond the schema, but the definition semantics are genuinely informative.

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 and resource ('create a BRAND-NEW workflow'), clarifies that it mints the workflow plus version 1, and describes what a workflow composes. It explicitly distinguishes itself from create_workflow_version in the closing sentence, so an agent can route without opening either 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 names the alternative for the adjacent case ('To add a version to a workflow that already exists, use create_workflow_version') and tells the agent a separate validate_workflow pass is unnecessary because validation runs inline. It also documents the publish=true shortcut for create-then-publish.

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