Conditional formatting

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

Annotations already signal non-read-only, destructive, and idempotent behavior; the description adds meaningful behavior beyond that by explaining how rule types behave: cell_is compares values, expression formulas are applied relatively from the top-left cell, and color_scale/data_bar are gradient and in-cell bar formats. This gives the agent a mental model of the mutation's semantics rather than only its safety profile.

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 two dense sentences with no filler. It front-loads the primary action, then systematically explains each rule type in an efficient, readable progression. Every sentence contributes necessary semantics.

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 12-parameter complexity, the schema's 100% coverage, and the presence of an output schema, the description supplies the missing conceptual glue: what each rule mode means and how fill/font relate to Excel's differential formats. It does not fully map every parameter combination per action, but it gives enough orientation for an agent to use the schema confidently.

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?

Although schema coverage is 100%, the description elevates the parameters by providing the conceptual framework: 'rule', 'operator', 'value', 'formula', 'fill_color', and 'font_color' are tied to actual Excel conditional-formatting behavior. It adds meaning beyond the terse schema field descriptions, such as the relative-formula semantics of 'expression' and the 'differential format' notion for fill/font.

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 — 'Lists, adds or clears conditional formatting' — and then defines exactly what conditional formatting is: rules that colour cells by their contents. It clearly separates this from sibling formatting tools like xlide_format_cells by focusing on rule-driven, condition-based formatting.

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 makes the tool's domain unmistakable: use it whenever conditional formatting rules need to be listed, added, or cleared. It does not explicitly name alternatives or say when not to use it, but the context is clear enough that an agent can route to this tool without confusing it with static formatting or validation siblings.

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