Find Rows

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

Description reveals key behaviors: raw value matching (numbers/dates by underlying value), and header row exclusion. These go beyond the readOnlyHint annotation, providing crucial context without contradictions.

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 concise and well-structured, using short sentences and front-loading the core purpose and key constraints. Every sentence adds value.

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 parameter interactions, matching behavior, and output format (row index). While it explains return value, it could note that the tool returns all row data? But given the context, it is sufficient and complete for a search tool.

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?

With 100% schema description coverage, the description adds meaning by explaining the mutual exclusivity of column/column_header, the meaning of match modes, and default behavior. It enhances understanding 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 description clearly states 'Searches a sheet tab for rows whose cell value matches query and returns each match with its 1-based sheet row index'. It distinguishes from sibling tools like get_sheet_data (returns all data) and update_row/delete_rows (uses the index).

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 guidance on restricting search by column index or header name, and notes that results can feed into update_row/delete_rows. It implies when to use this tool for targeted searches, but could explicitly mention it as an alternative to get_sheet_data.

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