split_column

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It is transparent about appending Table.SplitColumn to the M query and naming output columns, but it omits important side effects such as whether the original column is removed, error handling behavior, and impact on query folding.

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 front-loaded with a clear summary and then logically presents implementation details. Every sentence adds value without redundancy, making it appropriately sized and well-structured.

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 core transformation logic is thoroughly explained, but with no output schema, the description does not fully clarify return behavior beyond column naming. It also lacks discussion of side effects, error cases, and the role of standard parameters like partitionName. Given the moderate complexity, the description is adequate for the primary operation but incomplete for full context.

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 enriches the parameter semantics by explaining the `by` modes with illustrative examples (`','`, `'0,5'`, `'3,3'`) and clarifying the `parts` default value. This goes beyond the schema's terse descriptions, even though standard parameters like `sessionId` and `table` are not mentioned (schema coverage is 71%).

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 'split a text column into N new columns', specifying the verb, resource, and output. It distinguishes itself from the sibling split_column_to_rows by focusing on columns rather than rows, even if not explicitly naming the alternative.

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 detailed guidance on when to use each of the three modes (delimiter, positions, lengths) with concrete examples. It does not, however, state when not to use this tool or suggest alternative tools like split_column_to_rows for row-based splitting.

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