Audit workbook

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

Beyond readOnlyHint/openWorldHint, it discloses the important non-obvious trait that the tool recalculates the model first yet changes nothing else — critical, since an agent might otherwise fear a write. It also names the concrete contents of the returned JSON report, which the absence of an output schema would otherwise leave unknown. It stops short of noting cost/runtime on large workbooks.

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?

Front-loaded with verb, target, and return type, then the diagnostic list, then the routing sentence — a sensible order with no filler. The mid-sentence enumeration of report contents is dense and slightly list-heavy, but every item conveys actionable information.

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 burden of describing the return value and does so by naming each report category. Combined with the recalc-and-no-change behavior note and the sibling routing, an agent has everything needed to call it correctly.

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?

Only one parameter exists and the schema description already covers it fully (100% coverage), including the pointer back to create_session and list_sessions. The description adds no further meaning about the session_id, so this sits at the baseline for high-coverage schemas.

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 opens with a specific verb and resource ('Check a session's whole workbook') and then enumerates exactly what the check covers — broken/circular references, hardcoded plugs, external links, volatile functions, hidden sheets, stale caches, and a verification block. That enumeration lets an agent distinguish it from inspect_model, trace_dependencies, and diff_workbooks without opening the schema.

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?

It states the intended moment of use ('as a health check before trusting or handing off a model') and explicitly routes three alternatives by condition: inspect_model for structure only, trace_dependencies for a single value's lineage, diff_workbooks for two-file comparison. Both when-to-use and when-not-to-use are covered.

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