Google insights

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

Beyond the readOnlyHint annotation, the description discloses substantial behavioral context: a ~10 day data lag warning, comparison field details (prior, delta, deltaPercent), and a complete error-handling section with specific errorCodes and retryable flags. This exceeds what annotations alone provide and gives the agent actionable operational knowledge.

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 well-structured with clear sections: a one-line core purpose, followed by concise subsections for Comparison Options, Data Lag Warning, and Error Handling. Every sentence contributes essential operational knowledge, and the formatting makes it easy to scan. No redundancy or filler.

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 tool's complexity (6 params, enums, output schema), the description thoroughly covers usage nuances: aggregation choices, comparison semantics, data lag caveats, and error handling. The output schema handles return value structure, so the description focuses on decision-relevant behavior. This is a complete and self-sufficient description for an agent.

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?

With 100% schema description coverage, the baseline is 3. The description adds value by explaining the output effect of compare_with (inclusion of prior, delta, deltaPercent fields) and noting that 'total' aggregation yields 'maximum token reduction'—information not present in the schema. These additions help the agent reason about parameter consequences beyond mere syntax.

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 and resource: 'Fetch Google metrics for all locations, or a single location if storeId provided.' This clearly distinguishes the tool from siblings like get_google_ratings or get_google_reviews by scoping it to general Google insights, and the optional storeId parameter explicitly defines the single-location variant.

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 usage by explaining capabilities (aggregation, period comparisons) and datasets (Google metrics), but it never explicitly names alternatives or states when to use this tool versus a sibling. The behavior around comparison and data lag is context, not selection guidance. This is acceptable but not fully explicit.

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