formula_audit

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

Beyond the readOnlyHint annotation, the description reveals that actions return cached values, lists of FormulaErrorInfo, or cell refs, and notes the tool is read-only. This adds meaningful behavioral context without contradicting the annotation. The action-dependent return types are explicitly disclosed.

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 compact and well-structured with Args, Returns, and Notes sections. Every sentence contributes functional information, and the key behavior is front-loaded in the first line.

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?

Given the tool's complexity (5 params, enum, conditional requirements), the description covers all critical aspects: actions, parameter applicability, and return type categories. The presence of an output schema reduces the need to detail return structures further. Minor gaps include no explicit error-handling notes or cell format conventions, but these are not critical for correct invocation.

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 compensates by explaining each parameter's role: action values, file_path/sheet_name as workbook/sheet, and conditional requirements for cell_ref and cell_range. It lacks exact cell reference format but provides sufficient semantic mapping for an agent to invoke correctly.

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 action verb 'Inspect formulas' and enumerates five distinct operations (value, errors, precedents, dependents, list). This clearly distinguishes it from sibling write tools like formula_write and read_cells by establishing a focused audit scope.

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 clear context on when to use each action and which arguments are required (e.g., 'cell_ref: Required for "value", "precedents", and "dependents"'). It implies this is the go-to tool for formula inspection, though it doesn't explicitly name alternatives or exclusions.

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