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

Annotations already declare readOnlyHint, idempotentHint and closed-world, so safety is covered. The description usefully signals that the output is a generated formula rather than computed data, but it does not state what the returned string looks like, whether it must be pasted into a cell, or how locale/separator interacts with the generated syntax.

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?

A single front-loaded sentence that packs the verb, the resource and all five variants with zero filler. Nothing could be removed without losing 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?

With no output schema and three undocumented parameters, the description leaves real gaps: the return type (formula string), the multi-column restriction noted only in the range schema, and the meaning of order/ignore_case/skip_blanks. Adequate to start, insufficient to invoke confidently across all modes.

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?

At 33% schema coverage, the description partially compensates by giving semantics to the five mode values (list, count, counts, dupes, once). However, order, ignore_case and skip_blanks have no description text anywhere, and the description never mentions sorting, case folding or blank handling at all.

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?

States a specific verb and resource ("Build a formula for unique values") and enumerates the five output flavors, which an agent can map onto the mode enum. It never names a sibling, so the agent cannot tell from the description alone why this is preferable to sheets_filter_formula or sheets_rank_formula.

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 enumerated variants imply when the tool is appropriate (dedup, frequency counts, duplicate detection), but there is no explicit when-to-use vs when-not, and no routing to the sibling formula builders. An agent must infer the boundary from the variant list.

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