Compare two periods

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

The description goes well beyond the readOnlyHint/openWorldHint annotations by disclosing concrete behaviors: the comparison window defaults to an equal-length preceding period, yearOverYear uses 364 days to keep weekdays aligned, rows are matched on dimension values, results are sorted by absolute click change, and rows present in only one period are reported with zeroes. This is exactly the kind of behavioral detail an agent needs to interpret results correctly.

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 dense but efficient: three paragraphs each serve a distinct purpose — what the tool does, how the comparison period is selected, and how rows are matched and sorted. There is no filler or repetition of annotation information, and the most important information is front-loaded.

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 read-only comparison tool with no output schema, the description adequately covers input semantics, period selection, row matching, sorting, and treatment of missing rows. An agent can understand what the tool returns and how to configure it without needing additional context.

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 description coverage is 92%, so the schema already documents most parameters well. The description adds meaningful semantics beyond the schema: the meaning of the default comparison period, why yearOverYear uses 364 days, and the caution that using the date dimension makes comparisons meaningless. This improves parameter understanding without repeating the schema.

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 uses a specific verb ('Compare') and resource ('search-analytics query') and clearly states the return value ('per-row and total deltas'), which differentiates it from the single-period sibling query_search_analytics. The title and description align with the tool name, and the use-case list makes its purpose unmistakable.

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 gives explicit use cases ('is traffic up or down', 'what lost rankings', 'which pages grew') and explains the default comparison window and the three comparison modes. It does not explicitly name the alternative single-period tool or state when not to use it, but the context is clear enough that an agent can select it appropriately.

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