insert_columns

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

The description explains key behaviors via parameters: dry_run returns a plan without changes, inherit_before copies formatting from the left column. However, it does not disclose side effects like shifting existing columns to the right or potential data loss if columns contain data. Since no annotations are provided, the description carries the full transparency burden and only partially meets it.

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 extremely concise: one sentence for the core purpose followed by clean, bullet-like parameter descriptions. Every sentence adds value, and the structure front-loads the essential 'what it does' before details. No redundant or trivial information.

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 tool has 6 parameters, no annotations, and no output schema, the description covers all parameters and primary behavior. However, it lacks contextual information such as error handling, prerequisites (e.g., spreadsheet edit access), or a note about the resulting column shift. It also does not differentiate from sibling tools like insert_rows in terms of when to use each. Nonetheless, for a straightforward insertion operation, it is largely complete.

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 input schema has 0% description coverage, so the description provides all parameter meaning. Each parameter is explained with helpful details: spreadsheet_id_or_url accepts URL or ID, sheet accepts name or gid, start_column is a letter or 1-indexed number, count is integer, inherit_before and dry_run are booleans with clear purposes. This fully compensates for the schema's lack of descriptions.

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 action: 'Insert blank columns before the given column.' It specifies the resource (columns), operation (insert), and position (before given column). This is specific and distinguishes it from similar tools like insert_rows, which would insert rows instead.

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 lacks any guidance on when to use this tool versus alternatives such as insert_rows, delete_columns, or append_rows. It does not mention prerequisites (e.g., spreadsheet permissions) or context where this operation is appropriate. The usage is only implied by the tool's name and parameter list.

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