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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), and the description adds real behavior beyond them: formula values require pre-existing caches, formulas are not executed, and macros/external links/expansion bombs are refused. It also discloses that sheet names are preserved in metadata. Not a 5 only because it omits what happens on refusal (error shape) and the input size ceiling.

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 front-loaded sentences with no filler; the core action leads and edge-case behavior follows. Minor deduction for the vague qualifier 'genuine' UTF-8 CSV, which gestures at encoding details (BOM, quoting) without specifying them.

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?

An output schema exists, so return-value shape need not be described, and the description covers the important behavioral edges (formula caches, refusals, per-sheet splitting). The remaining gap is the input size limit and the failure mode when a workbook is refused.

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?

One parameter at 0% schema description coverage, so the description must compensate. It does clarify the encoding ('caller-supplied base64 XLSX'), which the schema only types as a bare string, but it never mentions the maxLength of 174764 (~128KB binary) — a hard constraint whose violation is a realistic failure mode and is documented nowhere else.

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?

States a specific verb and resource ('Extract every sheet from a caller-supplied base64 XLSX into separate genuine UTF-8 CSV files') and makes the one-to-many sheet-to-file mapping explicit. That directionality cleanly separates it from the sibling csv_to_xlsx without needing to name it.

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 conversion direction is implied clearly enough that an agent can infer when to pick this over csv_to_xlsx, but the description never states a when-to-use condition or names the reverse-direction sibling as the alternative. Usage is inferable rather than instructed.

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