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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavior: includes ads in ANY status, defaults to current month, returns per-row metrics plus _summary. This goes beyond the annotations and helps the agent understand side effects (none) and data scope.

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?

Three sentences, front-loaded with the core definition, then specific usage guidance, then return format. Every sentence earns its place; no fluff or repetition of schema/annotations.

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?

Given no output schema, the description does mention return contents ('per-row spend, revenue, ROAS, plus _summary') which partially compensates. With 5 params, no required params, and rich annotations, the description covers the main behavioral nuances (status inclusion, levels, default date range). Some param details like date format are missing, but overall complete enough.

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 0%, so the description must compensate. It explains 'level' with concrete options (ad, account, campaign) and gives default behavior for date range. However, it does not describe 'since', 'until', 'account', or 'auth_account' formats or semantics; the level guidance and default context help but leave gaps.

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 computes ROAS for a date range using Meta's /insights endpoint, names the specific resource (Meta ads insights), and distinguishes from siblings by covering ALL ad statuses (ACTIVE/PAUSED/DISABLED/ARCHIVED) and defaulting to current month. It also differentiates levels (ad/account/campaign) which separates it from other meta_ads_* tools.

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 explicitly says when to use which level: 'For account totals use level=account; for per-campaign view use level=campaign' and defaults to current month. It doesn't explicitly name alternatives among siblings (e.g., meta_ads_realtime, meta_ads_today) but the date-range/level guidance gives clear context. Missing explicit when-not-to-use, but adequate.

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