Compare user-supplied search reporting periods

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

The annotations already declare readOnly, idempotent, non-destructive, and openWorldHint=false, and 'No API calls' largely restates that closed-world, pure-computation property. The addition of 'no saved search properties or estimated traffic' does add genuine scope context, but there is no disclosure of output shape, rounding behavior, or how percentage-point change is computed.

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?

Two sentences, the operation and its output are stated first, and the exclusion sentence follows as a scoping caveat. No filler, no restatement of the tool name.

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, the description should signal what comes back; it names the key result (CTR percentage-point change) but not the full return shape or whether raw CTRs are included. For a simple four-integer pure computation that is adequate, though slightly thin on return values.

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 each parameter is already documented as nonnegative clicks/impressions in the earlier or later period. The description confirms the same framing ('caller-provided click and impression totals') but adds no format, unit, or edge-case guidance beyond the schema, so 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 ('Compare two periods') plus the concrete computation ('CTR percentage-point changes'), and scopes the inputs as 'caller-provided click and impression totals'. It distinguishes itself from the data-fetching siblings implicitly by ruling out saved properties and API calls, though it never names them.

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?

'No saved search properties, API calls or estimated traffic' effectively tells the agent when NOT to reach for this tool (i.e., when it needs live or estimated data from maestro_public_capabilities or maestro_explain_search_metrics). The when-to-use condition — the caller already has the four totals — is clear but stated indirectly rather than by naming an alternative.

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