Column statistics

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

The description lists the statistics returned, providing some output expectation, but it does not state whether the operation is read-only, how errors like missing files are handled, or the response format. Annotations are all false, so they provide no safety or side-effect context.

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?

Two sentences carry the full message with no filler; the usage directive is front-loaded and the statistic list is compact. Every sentence earns its place.

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?

Core purpose and output statistics are clear, but the definition is incomplete for an agent: it lacks sheet parameter semantics, output format, and read-only/side-effect guarantees. No output schema exists, so the description should carry more of this burden.

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 only 33%, and the description only adds meaning to path by allowing spreadsheet or CSV paths; columns already has a schema description. The optional sheet parameter is never explained, and no guidance is given about how it applies to CSV files.

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 identifies a specific operation: computing whole-column statistics (count, empty, distinct, min, max, sum, mean, median) for spreadsheet or CSV paths. It distinguishes the tool from built-in file readers, but it does not explicitly differentiate it from sibling sheet_* tools like sheet_read or sheet_query.

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?

It explicitly says to call this tool for any spreadsheet or CSV file path and states that built-in file readers cannot parse spreadsheets and must not be used. This is clear usage context, though it does not discuss when to prefer sheet_query/sheet_read or when not to use this tool.

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