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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is the audit semantics: each finding carries a fix, database findings come with a ready edit_db op, and 'Errors never block a save' tells the agent findings are advisory rather than blocking. It does not disclose cost or latency for large docs, but behavior beyond the annotations is genuinely clarified.

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?

It is dense and front-loaded by doc type, but written as long comma-spliced fragments that read like a checklist stuffed into one sentence. Every element is arguably relevant, yet the lack of sentence breaks and headers makes it harder to parse than a three-bullet structure would be.

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?

With no output schema, the description carries the return-shape burden; it does sketch the database design return (one line each, E/W/A, fix plus edit_db op) but is vague for sheets and Slides beyond 'with the fix for each', and does not say what a clean document returns. Adequate for a 6-parameter read-only audit tool, but not fully specified.

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 schema already documents all six parameters, and the description mostly restates them at a high level ('narrow with tables, level or rules', 'ignored adds what's ignored and why'). It adds slight meaning, such as that level/rules/tables/ignored apply only to database designs and that rules look like fk-no-index, but offers no additional format or interaction detail beyond the schema.

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 title and description state a specific verb (check/audit) and three resources (sheet, Slides, database design), and the description enumerates the concrete problem classes per doc type (formula errors, overflow, missing alt, fk-no-index). This distinguishes it from siblings like get, read, and edit_db, though the telegraphic fragment style makes the purpose slower to extract than it needs to be.

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?

Usage is implied by doc type, and 'narrow with tables, level or rules' hints at scoping, but the description never says when to use this versus get/read (inspect vs. audit) or when to precede edit_db/edit_sheet with a check. No explicit exclusions or prerequisites such as required permissions on the doc.

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