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

Annotations already provide idempotent/read-only/destructive hints. The description usefully adds that this saves a draft rather than publishing, and that repeated iteration is expected. It doesn't detail overwrite behavior, but the idempotentHint covers repeated-call safety.

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 front-loaded with purpose, then carries an IMPORTANT usage call and practical content guidelines. The second paragraph is long but justifiable because it specifies exactly what title and description content the agent should produce.

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 description is largely complete: it specifies when to call the tool, what to include in the title and description, and an output schema exists to describe results. Minor gaps are explicit workflow_id semantics and clarification of draft-overwrite behavior, but neither is critical.

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?

With 0% schema coverage, the description compensates well: it defines title as a brief workflow description with an example, and description as detailed markdown covering pipeline, input, and output. workflow_id is not explicitly explained but is clearly implied as the target workflow from 'for a workflow'.

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 uses a specific verb and resource: 'Save a template draft (title and markdown description)' for a workflow, and clarifies this is a pre-publish iteration step. It distinguishes the tool from sibling update operations by framing it as draft-saving before library publication.

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 explicitly states when to call it: after every workflow is built or significantly modified. It also gives a clear context of iterating on template content before publishing, though it doesn't name alternatives or when-not-to-call cases.

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