find_cells

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

With no annotations, the description fully carries behavioral disclosure. It clearly states the tool is read-only, works while the file is open in Excel, returns every match with addresses, describes match semantics (exact/contains/regex), explains look_in values/formulas/both, reveals that formula cells use the last cached value, and mentions timeout guarding for pathological regex patterns. This is unusually thorough.

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 dense but every sentence adds value: search scope, result behavior, match/look_in semantics, formula caching, pagination, and read-only/open-file behavior. The only slightly opaque phrase is 'plural sibling of the single-target search location selector,' but it still earns its place by signaling the tool's relationship to a sibling.

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 core search behavior, accepted match modes, look_in choices, formula-cell nuance, pagination, read-only safety, and file-open compatibility, which is strong given no annotations. An output schema exists, so return-value details need not be repeated. However, the location parameter and match_case behavior are not clearly explained, leaving a small gap for fully 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 must compensate. It explains match, look_in, limit, offset, and the timeout behavior, and clarifies how formula cells are searched. However, it does not meaningfully explain path, sheet, location, or match_case, leaving some parameter semantics to inference despite the 0% schema coverage.

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: 'Search cell values and/or formulas across a workbook, sheet, or range' and clearly states the return behavior: 'return EVERY match with its unambiguous address.' It also distinguishes itself from a single-target search alternative via the 'plural sibling' note, making its purpose easy to identify among many sibling tools.

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 implies the intended use case: searching for multiple matches across a workbook/sheet/range, and notes the tool is read-only and works while the file is open. However, it does not explicitly state when to prefer this tool over siblings like get_cells, read_range, or query_range, nor does it 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.