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

Annotations already declare destructiveHint=true, but the description adds the details that matter: what is destroyed (scheduled runs cancelled, email address released), that a confirmation prompt intervenes, and the exact recovery semantics of restore ('with its steps and versions, turned off'). That is well beyond annotation coverage.

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?

Two tightly packed sentences, front-loaded with the action and its consequences, then the confirmation rule and recovery path. No filler or restatement of the tool title.

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?

An output schema exists so return values need not be explained. For a single-parameter destructive tool, the description covers consequence, safety behavior, and reversibility – everything an agent needs to decide and act.

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% and workflowId is undocumented in both schema and description. The description does not explain where to obtain the workflowId (e.g., from workflow.list) or that it must be a UUID. The single parameter is largely self-evident, keeping this at minimum viable rather than failing.

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 ('Delete a workflow') and immediately enumerates the concrete effects: turns off, cancels scheduled runs, frees the sheet's email address. This clearly separates it from adjacent siblings like workflow.unpublish or workflow.toggle, which would not free the email address or cancel runs.

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?

Adds a concrete usage rule an agent must respect: 'This always asks the user first,' and points to workflow.restore as the reversal path. It does not explicitly contrast with workflow.unpublish or workflow.toggle, so the agent must infer when deletion is preferred over mere deactivation.

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