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

Annotations only mark readOnlyHint=false, but the description goes far beyond: it reveals the output format (id, url, bytes, durationMs, format, signed link valid for one hour), explains formula expansion in totalRow, notes that headers are always bold on tinted fill (no flag), warns about monthly quota, and describes what happens without an API key. This adds extensive behavioral context without contradicting any annotation.

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 efficiently packed into a few sentences, each earning its place: core purpose, structural details, sibling differentiation, output format, styling caveats, quota, and auth requirements. There is no repetition of schema information that is already clear, 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?

Given the complexity (nested sheets, columns, totalRow) and the lack of an output schema, the description covers the key behavioral aspects: return structure, formula handling, styling, auth, quota, and next-step conversion. It omits error cases and synchronous behavior (implied by the return structure), but these are secondary. The schema already constrains row count and width limits, so the description doesn't need to repeat them.

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 100%, so the baseline is 3. The description adds value by explaining the formula-expansion behavior for totalRow (bare aggregators like 'SUM' transform into real formulas, '=' prefixes go verbatim), clarifying that title is the filename stem, and noting the header styling (bold, tinted fill) which relates to the columns parameter. These details improve the agent's understanding beyond the schema alone.

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 starts with 'Build an Excel (.xlsx) workbook from a sheet spec', using a specific verb and resource. It details the input structure (columns, rows, number formats, total row) and explicitly distinguishes itself from sibling tools render_pdf and render_docx, making the tool's purpose unmistakable.

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 provides clear guidance on when to use this tool versus render_pdf ('when the recipient will sort, filter or recompute') and render_docx ('when the content is tabular rather than prose'). It also mentions the API key requirement, quota impact, and a downstream option (convert_document). It does not explicitly state when not to use it, but the context is strong enough for an agent to decide.

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