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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds value beyond those: the draft is created disabled by default and no credits are spent, which is meaningful cost/mutation context for a create operation. It does not, however, describe what happens on name collisions or whether repeated calls stack drafts.

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, zero filler, and the most decision-relevant fact (it saves a disabled draft, not a published workflow) is front-loaded. Every clause earns its place.

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 create tool with no output schema and opaque nested input objects, the description covers the workflow sequence and safety profile well but leaves parameter semantics almost entirely to the referenced schema tool. Adequate for orchestration, incomplete for construction of the definition payload.

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?

The schema has 5 parameters with 0% description coverage, two of them (definition, settings) are opaque nested objects, and the description explains none of them. The only partial compensation is the instruction to read get_workflow_schema first, which hints at how definition should be built, but name, project_id, and description semantics are entirely undocumented.

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 with scope: 'Save a new disabled workflow draft.' Immediately distinguishes itself from publish_workflow ('does not publish'), validate_workflow, and update_workflow by naming the draft state. An agent knows exactly which lifecycle stage this tool occupies.

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 procedure: read get_workflow_schema first, validate the draft, then publish explicitly. It names the prerequisite sibling and the follow-up sibling, and implies the exclusion (this tool does not publish). Nothing about when to use this vs. alternatives is left to inference.

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