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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states that nothing changes in the workbook, that the engine previews edits on the current revision, reports what would change and whether errors appear, and that a person decides whether to apply. This is transparent about side effects and the decision boundary.

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?

The description is compact and front-loaded: scope and input examples come first, followed by the no-side-effects guarantee, usage guardrails, and the follow-up action. Every sentence adds operational value with 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?

The description covers the whole proposal lifecycle: read first, propose edits, preview reports, then apply using proposal_id. It addresses safety, constraints, and next steps. Minor gaps remain around the exact structure of the returned report and optional parameter behavior, but the description is sufficient for correct invocation.

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%, so the description must compensate. It explains the main 'edits' parameter with examples and the 20-cell limit, but it does not clarify the optional 'sheet' and 'reason' parameters, nor the expected format of cell references. The required parameter is well covered, but optional inputs remain ambiguous.

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 states a specific verb ('propose') and resource ('contents for up to 20 cells'), with concrete examples of valid inputs like formulas or numbers/text. It clearly differentiates this from sheet_apply and sheet_read by emphasizing that nothing changes in the workbook and that a proposal_id is later applied.

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 operational guidance: read the cells first, avoid overwriting input numbers unless instructed, and then call sheet_apply with the proposal_id. This is a clear workflow with preconditions and next steps, which is more than merely stating when to use the tool.

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