set_column_widths

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 discloses auto-backup mechanics, the backup=False nuance ('skips rotation only'), atomic validated save, and the Word-open refusal condition. This is substantial beyond the bare operation, though permission requirements and post-failure state are not covered.

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 three terse sentences: purpose first, then backup/save semantics, then a clear failure condition. Every sentence earns its place, there is zero filler, and the most actionable information is 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?

Given this is a mutation tool with no annotations but an output schema, the description covers purpose, units, backup behavior, and a key refusal condition. It stops short of explaining table_index indexing or width validation constraints, but a competent agent would likely invoke it correctly with the provided information.

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 does clarify widths_pt by giving the unit (points) and the requirement of one value per grid column, and it adds backup behavior details. However, file_path and table_index are only named in the schema without explanation of indexing base or document scope, leaving moderate 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 opens with a specific verb-resource pair: 'Set every grid column width in points.' This distinguishes it from sibling tools like set_columns (page columns) and set_cells_block (cell content/formatting). The phrase 'one value per grid column' further defines the exact operation scope.

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 intended use is implied clearly—set grid column widths—but there is no explicit guidance about when to prefer this tool over alternatives like set_columns, format_cells, or apply_table_style. The refusal condition ('Refuses documents open in Word') provides operational context but does not serve as alternative-selection guidance.

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