Get Impressions

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

Beyond the annotations, it discloses the non-obvious side effect that the first call initiates report generation, the latency (up to two days), data retention windows, quota behavior (no Data API units), and a required API enablement step. This is exactly the context annotations cannot carry, and readOnlyHint=false is consistent with the described side effect.

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 data it returns and the Analytics contrast, then the setup caveat. Dense but nearly every clause carries information; the retention sentence ('keeps daily reports for 60 days, those first 30 days for 30') is slightly awkward to parse.

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?

Covers setup, first-call latency, date-range bounds, quota, and metric units, and an output schema exists to describe return values. Nothing essential to calling it correctly is missing.

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 parameters are already documented, but the description adds meaningful constraints beyond the schema: 60-day report retention and the 30-day limit on the initial window directly bound what `since`/`until` can return, and the ctr explanation (0.05 = 5%) clarifies the output unit.

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 concrete resource (thumbnail impressions and click-through rate) and explicitly positions it against the closest sibling, get_analytics, by noting YouTube Analytics doesn't offer this data. An agent can distinguish it from get_analytics without opening either schema.

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?

Explains the key operational context: the first call triggers report generation, results take up to two days, and the YouTube Reporting API must be enabled. It implies selection versus get_analytics but never states an explicit 'use get_analytics instead when you want views/revenue' rule.

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