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

Annotations already declare destructiveHint=true and idempotentHint=true, so the baseline is low, yet the description adds real consequence detail: rows are preserved, deleting a DASHBOARD view also destroys its dashboard, default views are protected, and a confirmation step is mandatory. It also discloses a return-value hint ('the result names the restore tool') that is not visible from the annotations alone.

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?

Four short clauses, front-loaded with the primary effect and its data-safety consequence before the edge cases. Dense and largely waste-free, though the sentence about the user prompt and the final sentence about the restore tool could be merged for tighter flow.

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 annotations covering safety and an output schema covering return values, the description only needs to add edge cases and workflow – which it does thoroughly. The remaining shortfall is parameter-level completeness for sheetId, which neither the schema nor the description explains.

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 coverage is only 50% – viewId is documented as coming from sheet.schema, while sheetId carries no schema description at all. The prose implies the sheet/view relationship and hints that viewId may denote different view types (DASHBOARD), but it never clarifies what sheetId must be or that the view must belong to that sheet, so it only partially compensates for the gap.

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?

'Delete a view from a sheet; its rows stay' names a specific verb and resource and immediately distinguishes this from sheet.delete by stating that rows survive. The DASHBOARD caveat further separates view types, so an agent can tell this apart from view.create, view.restore and sheet.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 gives an explicit precondition ('say which view goes before you call it') and an explicit exclusion (the sheet's default view cannot be deleted), and it points to the recovery path via the restore tool named in the result. An agent knows both when to call it and what to do around it.

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