format_cells

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

With no annotations, the description carries the full behavioral burden and does well: it discloses auto-backup behavior with '.ks4w-backups', clarifies that backup=False only skips rotation, mentions atomic validated save, and warns about Word-open refusals. It does not describe the output/return shape, but an output schema exists, so that gap is acceptable.

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 compact yet information-dense: purpose first, then target/formatting syntax, then backup and behavioral caveats. Every sentence adds operational value, and there is no repetition of schema fields beyond what is necessary for clarity.

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 nested parameters, no annotations, and 0% schema description coverage, the description covers the essential calling semantics: target selection, formatting attributes, backup behavior, and an important failure condition. It lacks explicit usage routing to sibling tools, but the core information needed to invoke it correctly is 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 0%, so the description must compensate. It meaningfully explains targets with '[{row, cell?}]' and the special whole-row shorthand, lists the formatting object's keys, and clarifies the backup parameter's semantics. file_path and table_index are left to their names, but those are self-evident.

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 opening phrase 'Format table cells in bulk' states a specific verb and resource, and the enumerated formatting fields (shading, bold, italic, alignment, etc.) make the operation concrete. It does not explicitly name a differentiating sibling, but 'bulk' and 'formatting' clearly separate it from value-setting tools like set_cells or set_cells_block.

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 use for bulk cell formatting and gives a hard constraint with 'Refuses documents open in Word.' However, it never explicitly says when to prefer this tool over alternatives like set_cells_block or apply_table_style, nor does it state when not to use it beyond the Word-open refusal.

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