audit_model

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

The description indicates the tool audits the workbook and returns a report, implying a read operation but without explicit statements about non-destructiveness or permissions. With no annotations, the description partially informs behavior but lacks completeness.

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 extremely concise, with two sentences: the first states the core action, the second adds reusable rule configuration and return type. No unnecessary words, and critical information is front-loaded.

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?

The description covers the tool's function and return type, and an output schema exists (not shown). However, it omits prerequisite context (e.g., workbook must be open) and does not address whether the audit modifies the workbook, leaving gaps for an agent.

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?

The sole parameter 'workbook_name' has no schema description, but the description connects it to the workbook being audited, adding meaning. For a single parameter, this is effective, though more detail (e.g., format or constraints) would improve clarity.

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 clearly states the tool runs a model audit against a workbook and returns an AuditReport with findings. However, it does not differentiate this tool from sibling tools like 'diagnose_workbook' or 'plan_risk_model', leaving some ambiguity about unique purpose.

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 no guidance on when to use this tool versus alternatives (e.g., 'diagnose_workbook'), nor does it mention prerequisites like workbook being open. The rule location details are implementation-focused, not usage-oriented.

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