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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces read-only while adding genuinely useful context: the 95-day cap, the keyword-ranking interval limits (90 DAILY / 31 RAW), the ratio-recomputation rule, and the exclusion for campaign scheduling dates. These are non-obvious behavioral constraints an agent would otherwise get wrong.

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 purpose is front-loaded correctly, but the body is a long block of date-splitting boilerplate that reads like shared policy text rather than tool-specific guidance, plus a keyword-ranking digression that this tool's schema doesn't even expose as parameters. Roughly half the text does not earn its place for calling this specific tool.

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?

Safety and date-window behavior are well covered, and an output schema exists so return values needn't be described. However, for a multi-signal diagnostic tool with an optional 'focus' param, the description never explains what kind of diagnosis is produced (drivers, attribution, anomaly breakdown) or how it differs from the two sibling diagnose_* tools.

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 100%, so the schema already documents storeId format and the per-date-range limits. The description adds the independent-limit rule for comparison ranges and the windowing formula (endDate = startDate + 94 days), which is somewhat more than the schema, but it says nothing about what the optional 'focus' parameter actually changes in the diagnosis.

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 opening sentence gives a specific verb (diagnoses), resource (sales changes), and names the signal sources (sales, traffic, advertising, inventory) and scope (one store, business date range). It implicitly distinguishes itself from the query_* siblings by being a diagnosis rather than a raw data pull, though it never names a sibling to contrast with.

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 gives real constraint guidance — split windows for longer ranges, don't average ratios, don't split advertising write plans, get a supported window from the user — but these are mostly operational rules for the date parameters rather than when-to-use-this-tool guidance. It never says when to pick this over diagnose_ad_efficiency, diagnose_profit_anomaly, or the query_* tools.

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