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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered and the description does not need to repeat it. What the description does add is real: it is a *deep* read rather than a summary, and 'Google accounts have the most here' discloses uneven coverage across platforms. It does not mention pagination, latency, cost of the deep read, or what happens for non-Google accounts beyond having less data.

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 opening clause is well front-loaded, but the body becomes a long semicolon-chained inventory of return fields that largely restates what the output schema already declares. Much of that enumeration could be trimmed without losing decision-relevant information, and the 'useful for' list would read better as its own sentence.

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 an output schema present, the field inventory is redundant rather than necessary, but the description still gives an agent enough to know what the tool covers and when it is the right call. The one remaining gap — how it relates to get_results / get_ad_set_health / list_accounts — is minor for such a broad, clearly scoped tool.

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%: 'account' already documents omit-for-all and 'language' documents the default. The description adds nothing about either parameter (e.g. whether account names are exact-match, whether language affects only prose or numbers), so the schema does all the work and baseline 3 applies.

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 names a specific resource and a distinct depth of read ('the deep read of each ad account ... the written review ... and the facts under it') and enumerates the concrete contents (impression share, search terms, quality score, conversion actions, devices, PMax spend, tracking switches). It is unambiguous what the tool returns, though it never names the sibling it supersedes (e.g. get_results or get_ad_set_health), so the boundary with those tools is left implicit.

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?

It gives concrete triggering questions — 'why', 'can we spend more?', 'what holds us back?', 'is tracking right?', 'which searches waste money?' — which is strong when-to-use guidance. It stops short of any when-not-to-use or explicit pointer to an alternative tool for lighter-weight result checks.

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