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

Annotations only supply readOnlyHint/openWorldHint; the description adds substantial behavior beyond them: only campaign types with ad groups are included (Search/Display/Video), PMax is excluded, today is excluded from the day range, and totals are explicitly NOT account totals. It also documents the report shape and the UNDETERMINED bucket semantics — rich context an agent cannot get from the annotations.

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?

Front-loaded with purpose, then scope constraints, then return shape. Dense but each line carries information; the return-structure detail is partly redundant given an output schema exists, which keeps it from a 5.

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 analytics tool with two params, it covers scope limitations, exclusion of PMax, alternative for account totals, and bucket semantics. Even though an output schema exists, the added explanation of UNDETERMINED buckets and non-account-total sums is decision-critical and complete.

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 0% schema description coverage, the description must carry the burden and does: 'days' is defined as last N days excluding today, and 'workspace' as the customer workspace slug, optional when only one workspace exists. Both parameters gain meaning beyond their bare types, though exact date anchoring for days could be sharper.

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 the specific resource (performance by age and gender) and its intended use (basis for B2B exclusions), then immediately distinguishes it from ads_campaign_performance for account totals. An agent can differentiate it from device/geo/schedule performance siblings by the dimension named.

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?

Explicitly names the alternative for account-level totals (ads_campaign_performance) and states the use case (B2B exclusions). However, it does not state when to prefer this over ads_device_performance or ads_geo_performance when an agent wants a broad breakdown, so a small inference gap remains.

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