find_duplicates

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

The readOnlyHint annotation already indicates a safe read operation. The description aligns with this and adds useful behavioral details by specifying the return format (dict with duplicate groups and row indices) and the basis for duplication (a list of columns). It does not contradict the annotations and adds context beyond the structured fields.

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 a compact, well-structured docstring with an Args section and Returns section. Every sentence provides relevant information without unnecessary fluff, making it easy to scan and understand.

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 adequately covers inputs and the return value, which is essential since there is no output schema. It lacks explicit differentiation from deduplicate_data and does not specify how duplicate groups are keyed or whether the first occurrence is included, but the overall tool behavior is clear enough for a tool of this complexity.

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 carries the full burden for parameter semantics. It documents all four parameters with clear, meaningful definitions: file_path as workbook path, sheet_name as worksheet name, columns as the basis for duplicates, and has_header as a header-row indicator. This fully compensates for the schema's lack of descriptions.

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's function with a specific verb and resource: 'Identify duplicate rows based on a list of columns.' It also differentiates from sibling tools like deduplicate_data by emphasizing identification rather than removal, and the return value of duplicate groups and row indices reinforces this.

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 usage for finding duplicate rows based on selected columns, but it does not explicitly state when to use this tool over alternatives such as deduplicate_data. No exclusions or alternative recommendations are provided, so guidance is only implicit.

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