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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered and the trailing 'Read-only' is redundant. The description still adds genuine behavior beyond the annotations: partial-failure handling ('Skips inaccessible accounts') and the report's contents (per-account metrics, grand total, underperformers), which tell the agent what to expect from the aggregation.

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?

Dense but front-loaded: the tool's identity and scope lead, then metrics, then failure behavior, then the parameter. Every clause carries information, though the em-dash chaining makes it a single run-on block rather than cleanly separated lines.

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 an output schema exists, return values need not be spelled out, yet the description usefully previews the metric set. Purpose, scope, failure behavior, and the lone parameter are all covered; minor gaps remain around time zone/currency and how 'selected' accounts are designated, since no selection parameter exists.

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 0% for the single parameter, so the description must carry the load; it does define 'days' as lookback days, which gives the parameter real meaning. It does not mention the schema's default of 30 or the time-unit granularity, so it only partially compensates for the coverage gap.

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?

States a specific verb (aggregates) and resource (ALL connected/selected Google Ads accounts into one report), and enumerates the exact metrics produced plus grand total and underperformers. The multi-account scope clearly separates it from single-account report siblings, though it never names the closest alternative (performance_report) 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 '(agency)' framing and 'aggregates ALL connected/selected accounts' implies when the tool is appropriate, and 'Skips inaccessible accounts' hints at robustness. However, there is no explicit when-to-use/when-not statement or routing to performance_report for single-account queries, so the agent must infer the choice.

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