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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered. The description adds that this is a diagnostic sweep across several signal types and surfaces 'problems that break optimisation', which is useful framing beyond the annotations. It does not disclose cost, latency, or whether a short window produces noisier results, so it stays at adequate rather than rich.

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?

One dense sentence with zero filler; every listed item (event counts, value presence, CAPI, problems) is substantive information about the output. It is slightly front-loaded on topic rather than action, opening with 'The account's pixels or datasets' instead of a verb.

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?

With no output schema, the description carries the burden of explaining return values, and it does so concretely by listing the five tracked events and the CAPI/value/problem checks. For a one-parameter read-only diagnostic this is close to sufficient; the remaining gap is the absence of any guidance on when to prefer this over get_account_health.

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?

Single optional 'days' parameter with 1-30 bounds, a default of 7, and 100% schema description coverage, so the schema fully documents it. The description adds nothing about the window - notably it never warns that the maximum is 30 days while other reporting tools may allow longer ranges. Baseline 3 is appropriate given the schema carries the load.

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 definition names a very specific resource (the account's pixels/datasets) and enumerates the exact diagnostics: last-fired timestamps, daily counts per standard event, value presence, CAPI server-side delivery, and optimisation-breaking problems. The content is unmistakably distinct from sibling diagnostics like get_account_health. It falls short of a 5 because it is a noun-phrase inventory with no explicit verb and no direct statement of how it differs from the account-level health check.

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?

There is no when-to-use guidance, no prerequisites, and no named alternative or exclusion. An agent must infer from the name that this is the tool to reach for during pixel/tracking troubleshooting rather than before launching a campaign.

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