google_ads_performance_report

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

The description states 'Read-only; no mutation,' which is crucial since no annotations are provided. It also describes the return structure with exact field names. While it doesn't cover error conditions or data availability, it sufficiently discloses the tool's behavior and output format.

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 description is concise with no filler sentences. It front-loads the core action, then lists metrics, and ends with usage guidance. It earns its length, though it could be slightly more compact for readability.

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?

Despite the absence of an output schema, the description details the return shape and metric fields. It covers the main use case and constraints. It does not mention error handling or performance notes, but for a straightforward report tool, it is fairly 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?

Schema coverage is 100%, so baseline is 3. The description adds extra semantic guidance beyond the schema, such as recommending shorter windows for diagnosing recent changes and LAST_90_DAYS for trend baselines for the 'period' parameter, which helps agents choose appropriate values.

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 description clearly states the tool aggregates campaign-level performance metrics over a reporting window, with a specific verb ('Aggregate') and resource ('campaign-level performance metrics for a Google Ads account'). It distinguishes from siblings by naming four alternative tools for different granularities.

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 explicitly says 'Use this for campaign-level totals' and then provides explicit alternatives: per-ad breakdowns, network splits, query-level detail, and conversion-action slicing, each linked to specific sibling tools. This provides clear when-to-use and when-not-to-use guidance.

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