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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds two genuinely non-obvious traits: the result is rendered as a card, and the comparison baseline is the previous period of equal length by default. It says nothing about latency, data freshness, or how large a window is practical, so it stops short of rich behavioral context.

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 short sentences, front-loaded with the purpose, then the attribution scope, then the default window. Nothing is redundant and no sentence merely restates the 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 eight optional parameters and no output schema, the description covers what the tool does, what it breaks the change down by, and the default time comparison. The main remaining gap is the account-versus-folder scoping decision, which is left entirely to the parameter descriptions.

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%, so the enum and date parameters are already fully documented and the baseline would be 3. The description earns an extra point by defining the comparison semantic — selected period versus the immediately preceding period of equal length — which the schema never states, and by hinting at the breakdown dimensions returned.

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?

"Explain why a metric changed" gives a specific verb (explain/diagnose) plus a specific resource (metric change), and it names the breakdown dimensions it attributes the change to (campaigns, devices, networks). That distinguishes it from reporting siblings like google_ads_performance or google_ads_breakdown, though those alternatives are never named explicitly.

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 its use case — answering "why did this metric move" — and supplies a default comparison window, but it never states when to pick it over google_ads_performance, google_ads_breakdown, or google_ads_change_history. There are no exclusions or prerequisites, so the agent has to infer routing from the verb alone.

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