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

Annotations only declare it is a non-destructive, non-idempotent write; the description adds real substance beyond that — hard caps of 50 columns, 1,000 rows, 1,000 characters per cell and a 24,000-byte markdown limit, plus the rule that formulas begin with '='. It stops short of explaining what happens when a limit is exceeded or how the caller obtains the key material, which keeps it out of the top band.

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?

Sentences are short and the hard limits are front-loaded where an agent will read them first. The signing-payload sentence is dense and packs nested literal syntax and a module path into one line, but no sentence is 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?

For a 9-parameter, 8-required mutation tool with zero schema description coverage and no output schema, the description covers limits, formula syntax, and payload construction reasonably. It still leaves the agent without guidance on how to generate publicKey/signature/timestamp/nonce or what a success response looks like, which is a meaningful gap at this complexity.

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 carries the burden; it explains columns as the header row, rows as data cells, the Sheet1 name default, and the shape of the signed payload. But publicKey, timestamp, nonce, signature, and kind are only gestured at through the payload example — no format, source, or provenance for the signing fields.

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 first sentence states a specific verb and resource ('Create a spreadsheet'), and the rest of the description is unambiguously about spreadsheet creation. However, it never distinguishes itself from sibling tools like create_markdown or edit_spreadsheet, so the agent must infer which creation tool applies from the resource name alone.

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?

There is no statement of when to use this tool versus create_markdown, edit_spreadsheet, or suggest_edit. Constraints (column/row/byte limits) are stated, but those are behavioral limits, not selection guidance; the agent gets no explicit routing signal.

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