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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description adds the cascade scope, the mandatory user confirmation step, and the critical exception that File List field files are unrecoverable even after restore. That is exactly the behavioral context an agent needs before firing a destructive call.

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: what gets destroyed, what the agent must do first, what can and cannot be recovered. Front-loaded with the blast radius and 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?

Output schema exists so return values need no explanation; the description covers the destructive scope, the confirmation protocol, and the irreversibility exception. Nothing an agent needs to call this safely is missing.

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% for the single sheetId parameter, and the description never clarifies its meaning or format. The parameter name is largely self-explanatory and there is only one, so the gap is minor rather than crippling, but the description does not compensate for the missing schema documentation.

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 first sentence names a specific verb (delete) and resource (sheet) and immediately enumerates the cascade scope (rows, views, forms, dashboards, workflows), which no sibling implies. An agent can distinguish it from sheet.update, item.archive or folder.delete without opening a 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?

It states an explicit precondition for invocation ('say what goes before you call it') and names the recovery alternative, sheet.restore. It stops short of saying when NOT to delete (e.g. archive instead), but the when-to-use signaling is unusually concrete.

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