data_cleaner

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

The description discloses some behavioral traits: preview mode 'without persisting changes', ordered operations, and a return summary. However, it does not clarify whether changes are written in-place to the original file or only to output_file, what happens if output_file is omitted, or side effects on existing data. The note 'Document allowed operations strings in the route or underlying tool docs' reveals a documentation gap, and with no annotations, the description carries the full burden.

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 structure is clear and efficient: a one-sentence purpose, an Args list, a Returns section, and a Notes section. The Notes section contains a developer-facing meta-comment about documentation, which is less useful for an agent, but overall the description is well-organized and 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?

This is a high-complexity tool (9 parameters, no output schema, no annotations) and the description is not complete enough. It does not specify the default persistence behavior (in-place vs output_file), the interaction between fill_missing_strategy and fill_value, or the exact content of the return summary beyond 'rows modified and operations applied'. The note about missing operation documentation further reduces completeness.

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 description lists all 9 parameters with brief explanations, adding meaning beyond the schema's bare titles. It provides useful clarifications such as 'preview: If True, return a preview without persisting changes' and 'fill_value: Literal value to use if strategy is "value".' However, it does not explain default values or enumerate allowed fill strategies or operation names, referencing external docs instead.

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 purpose: 'Run a pipeline of cleaning operations (trim, dedupe, fill missing, normalize, etc.) on a sheet.' This specifies a verb, resource, and scope, and differentiates it from sibling tools like deduplicate_data or find_duplicates by emphasizing a multi-step pipeline.

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 cleaning workflows but does not explicitly state when to use this tool versus alternatives. It does not mention exclusions or point to specialized sibling tools for single operations. The note about documenting allowed operation strings hints at intended flexibility but does not guide selection.

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