create_column

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

No annotations are provided, so the description carries the full burden. It mentions support for dry_run, which is a behavioral detail, but it does not disclose other important behaviors such as transactionality, whether the operation is reversible, what happens if the column already exists, or any error conditions. For a mutation tool with 13 parameters, this is a significant gap.

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 concise at two sentences, front-loading the purpose. The list of supported properties is dense but useful given the lack of schema descriptions. It avoids unnecessary fluff and is well-structured. The only minor inefficiency is the redundant mention of 'description' when it's not in the schema, but overall it is appropriately sized.

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?

Given the complexity (13 parameters, no output schema, no annotations), the description is incomplete. It does not cover error handling, return value, prerequisites, interaction with transactions (siblings like begin_transaction exist), or how dry_run behaves in practice. An agent calling this tool would need to guess about these aspects, making the description insufficient 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?

Schema description coverage is 0%, so the description must compensate. It lists and explains many parameters (name, code, data_type with examples, length, precision, mandatory, default_value, comment, domain, primary), providing meaningful semantics beyond the bare schema. However, it omits explanation for model_id and table_ref (though these are self-evident) and incorrectly mentions a 'description' property that does not exist in the schema, which could confuse. Overall, it adds substantial value but has minor gaps.

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: 'Add a column to a table.' This is a specific verb+resource, and it distinguishes itself from sibling tools like update_column, rename_column, and delete_column by focusing on creation. The supported properties list further clarifies scope without ambiguity.

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 creating a new column, and the presence of sibling tools like update_column and delete_column makes the intent clear. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites (e.g., model must be open). The guidance is implied rather than explicit.

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