Get performance insights

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

Annotations only declare readOnlyHint and openWorldHint, but the description adds substantial behavioral context the annotations cannot: spend is in account currency units (not micros), today's attribution metrics are preliminary, dates are inclusive and in account timezone, and until defaults to yesterday. These are exactly the kinds of caveats an agent needs before trusting the numbers.

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 the report's purpose and metrics, then flows through date range, scope, segment, currency/caveats, and advanced options. Dense but every clause carries distinct information with no filler.

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 14-parameter, no-output-schema, open-world reporting tool this is close to complete: it covers dates, scoping, segmentation, currency semantics, and advanced fields/filters/sort. It omits pagination (limit) and time_granularity guidance, which an agent would need for large result sets.

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 only 21% across 14 parameters, so the description must compensate and largely does: it explains since/until format and inclusivity, last_n_days default of 7, the three id-scoping params, the segment enum values, and that 'fields' accepts canonical names like 'campaign.roas'/'ad.cpa'. Gaps remain for limit, after, and time_granularity, which are never mentioned.

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+resource ('Performance report') and enumerates the exact metrics returned (impressions, clicks, spend, CTR, CPC, CPM) plus the supported aggregation levels. This clearly separates it from sibling tools like account_summary, get_campaign, or list_ads, which do not return a multi-metric report.

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?

Gives rich operational context: two alternative date-range mechanisms with defaults, entity scoping via campaign_id/ad_group_id/ad_id, optional single-dimension segmentation, and an 'Advanced' path for canonical fields, filters and sort. It does not explicitly name a sibling tool or state when-not-to-use, so it stops short of a 5.

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