update_column

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

The description is highly transparent about conversion behavior: it converts existing values, clears unconvertible ones, and reports conversion counts in the response. However, annotations declare destructiveHint=false while 'clears the ones that cannot convert' describes a data-destroying side effect. This is a direct annotation contradiction, so the score is 1 per rubric.

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?

Three dense, purposeful sentences with no filler. The first sentence front-loads the main operations, the second explains the critical conversion side effect, and the third adds validation context. 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?

For a mutation tool with no output schema, the description covers the main invocation surface, dangerous side effects, and response clues. It does not describe the full success response format or clarify when force should be used, but those are minor gaps given the richness already present.

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 30%, but the description adds real parameter meaning: rename maps to name, type change maps to type, settings replacement maps to settings, and isRequired/isHidden are explicitly called out. It also adds conversion semantics and validation behavior. Identifier parameters are self-explanatory, and force already has a schema description.

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 states a specific verb ('Change') and resource ('a column'), then names the exact operations: rename, change type, replace settings, set isRequired/isHidden. This clearly distinguishes it from sibling tools like create_column, delete_column, and reorder_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?

'Change a column after the fact' gives clear context that this tool targets existing columns rather than creation-time configuration. It does not explicitly name create_column as the alternative or list when-not conditions, but the contextual signal is strong.

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