Calculate CTR from supplied search aggregates

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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real value beyond them: it declares the output unit (a percent) even though there is no output schema, and the 'no external queries or stored credentials' line reinforces the closed-world hint in concrete terms.

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?

Three sentences, formula first, then the validity constraint, then the no-side-effects note. Nothing is redundant and every sentence carries information an agent needs before calling.

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 two-integer arithmetic tool with full schema coverage and no output schema, the description supplies everything needed: the operation, the unit of the result, and the input-consistency requirement. There is no residual ambiguity an agent would have to resolve at call time.

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 coverage is 100% and both properties already document clicks and impressions as totals from one source and period. The description's consistency requirement (same source, period and filters) restates what the impressions parameter description already says, so it adds almost no new meaning. Baseline 3 applies.

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 gives a specific verb and resource — compute clicks divided by impressions as a percent — so there is no ambiguity about what comes out. It does not name or distinguish any sibling (maestro_compare_periods, maestro_explain_search_metrics), but those perform different jobs, so the omission is minor rather than disqualifying.

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?

It clearly states the precondition for correct use: all numbers must represent the same search source, period and filters. It also clarifies that inputs come pre-supplied rather than being fetched. What it does not do is say when to avoid this tool or which sibling to use instead of computing CTR by hand.

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