delete_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 clearly states the success return format ('v:{new_hash}') and error format (JSON with error and message fields), which is important for an agent to interpret results. It also implies destructive action via 'delete' but does not explicitly state that the operation is irreversible or any permission requirements. The optimistic concurrency mechanism via version is transparent, adding value beyond the schema.

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 efficiently structured: a one-line summary, then return behavior, then a parameter list. It front-loads the essential purpose and prerequisites, and every sentence adds value. There is no fluff or redundancy, and the format is scannable for an agent.

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?

For a tool with 4 required parameters, no output schema, and no annotations, this description covers all essential aspects: purpose, preconditions (version hash), parameter semantics, and return format. It also implies error handling. While it does not enumerate edge cases (e.g., stale version, non-existent column), the error JSON mention covers general failures. Given the tool's complexity and the lack of structured metadata, the description is comprehensive and sufficient for correct invocation.

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 must fully compensate for missing parameter documentation. It does this admirably: file_path is defined as 'Absolute path to the Markdown file,' table_index as '0-based table index from list_tables,' version as '12-char hex hash from read_table (after "v:"),' and column as 'Column letter ("A"), name ("Priority"), or composite ("B:Priority").' This level of detail far exceeds what the schema provides and gives the agent precise instructions for each argument.

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 opens with a clear, specific verb and object: 'Delete a column.' It also specifies the required dependency on a version hash from read_table, which distinguishes it from sibling tools like insert_column and rename_column. The distinction is clear and unambiguous.

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 explicitly states the prerequisite of obtaining a version hash from read_table, which guides the agent on when to call this tool (after read_table). It does not explicitly state when not to use it or mention alternatives like insert_column or rename_column, but the verb 'delete' and the parameter details strongly imply the use case. A brief mention of alternative tools would push this to a 5.

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