Clear a range in a Google Sheet

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the destructive nature is known. The description adds valuable behavioral context beyond that: the two-call confirm flow, the echo mechanism (confirmCells) that catches naming mistakes, the fact that there is deliberately NO default range, that the clear is read back and reported as confirmed only if the range is truly empty, and that rows are left in place. This is rich, non-obvious behavioral disclosure that goes far beyond the structured data.

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?

Every sentence earns its place. The description front-loads what the tool does, then explains the safety protocol, the echo rationale, the no-default-range design, and the alternative tool — all in roughly 110 words. Nothing is wasted or redundant with the schema or annotations.

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 destructive mutation tool with 5 params, no output schema, and only partial schema coverage, this description is remarkably complete. It covers the operation, the safety workflow, the exact parameters to set in each call, a common failure mode, the absence of a default, the post-condition verification, and points to the sibling for a related but different task. There is no meaningful gap an agent would face when invoking it correctly.

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 only 40%: 'range' and 'confirmCells' have descriptions, but 'confirm' and 'sheetUrl' and 'spreadsheetId' do not. The description partially compensates by explaining confirm (the two-call protocol) and confirmCells (echo the filled-cell count the unconfirmed call reported). It doesn't explain the relationship between sheetUrl and spreadsheetId, but the core usage semantics of the non-obvious parameters are well covered. With 5 params and 40% coverage, the description carries a large share of the burden and does so effectively.

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 description clearly states the verb 'Empty a range of cells in a Google Sheet' and specifies a resource (cells in a range) and scope (leaving rows in place). It distinguishes itself from the sibling manage_sheet_tabs by explicitly naming it as the alternative for removing a whole tab, and from other sheet operations by focusing specifically on clearing a range.

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?

The description gives explicit when-to-use and how-to-use guidance: call once without confirm to get the filled-cell count, show the user that number, get confirmation, then call again with confirm:true AND confirmCells set. It also explicitly names the alternative for a different task: 'To remove a whole tab instead, use manage_sheet_tabs.' This is exactly the kind of exclusionary guidance that helps an agent decide.

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