expand_column

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

With no annotations, the description discloses that it appends Table.ExpandRecordColumn/ExpandTableColumn/ExpandListColumn to the table's M query, which is an important behavioral trait. It also explains parameter interactions (fields ignored for list). It does not cover error handling or reversibility, but the core behavior is well conveyed.

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 concise sentences: the first states purpose, the second packs parameter behavior. No redundancy, well 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?

The description successfully explains the operation and key parameters, but lacks details on return values, error conditions, or prerequisites. With no output schema or annotations, the agent may require additional inference about side effects.

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 schema already has 67% coverage and good descriptions for kind and fields. The description adds the 'ignored for list' behavior and clarifies the default kind, though the schema's null default slightly conflicts. It doesn't add semantics for sessionId, table, or partitionName, but these are self-explanatory.

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 action ('surface inner fields of a structured column') and identifies the specific M functions appended. This distinguishes it from sibling tools that focus on other transformations like split_column or merge_columns.

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 provides clear context: the tool is for expanding structured columns in Power Query using record/table/list semantics. It does not explicitly list alternative tools or exclusions, but the usage scenario is unambiguous.

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