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

Annotations already declare destructiveHint=false and readOnlyHint=false, but the description adds genuinely new behavioral facts: the draft is created disabled and no credits are consumed, so the agent knows this is a side-effect-light mutation. It leaves out what makes the operation non-idempotent (duplicate calls creating duplicate drafts) and any name-collision behavior.

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?

Three short sentences, each doing distinct work: what it creates, the negative scope (no publish, no credits), and the required call sequence. The most decision-relevant clause is front-loaded with no 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?

With nested `definition`/`settings` objects, 0% schema coverage, and no output schema, the description should say more about the shape of a valid draft and what comes back (draft id?). The lifecycle guidance is solid, but an agent still lacks what it needs to fill in the two required parameters confidently.

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% across five parameters, so the description must carry the load and it mentions none of them by name. The instruction to read get_workflow_schema hints that `definition` must follow that schema, but the roles of name, project_id, settings, and description go entirely unexplained.

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 ('Save a new disabled workflow draft') and immediately draws the boundary against the publish path ('Does not publish or spend credits'). This makes it clearly distinguishable from publish_workflow, validate_workflow, and update_workflow 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?

Gives an explicit ordered pipeline naming siblings: read get_workflow_schema first, validate the draft, then publish explicitly. It does not state the counterpart case (e.g., use update_workflow to modify an existing draft rather than re-creating), so the routing guidance is strong but not exhaustive.

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