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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the safety profile is covered without the description. The description adds no behavioral context of its own: nothing about latency, rate limits, whether results reflect Meta-side attribution windows, or how the openWorld external fetch behaves on failure.

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 two sentences overlap heavily, both listing spend and ROAS and conversions, so the reader parses the metric list twice instead of getting one authoritative set with any scoping caveats front-loaded. Front-loading is fine but roughly a third of the text is duplication.

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?

There is no output schema, and the metric enumeration partially compensates by telling the agent what comes back. The gaps that remain — the level of aggregation, currency, and whether different accounts produce comparable scales — are not addressed, which matters for the stated 'compare brands or clients' use case.

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 100% and the schema already documents ad_account_id's act_… pattern with provenance from list_ad_accounts, plus the full enum of date presets. The description only restates 'date range' and 'per account', so baseline 3 applies — no meaning is added beyond the structured fields.

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 first sentence names a concrete resource (one Meta ad account) and concrete outputs (spend, ROAS, CPA, conversions) over a date range, and the second sentence enumerates the full metric set. It is clearly an account-level aggregate report, distinguishable from ad-level siblings like get_ad_performance_by_device, though it never names a specific sibling to contrast with.

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?

"call it per account to compare brands or clients" gives one concrete usage scenario, which is more than nothing. However it offers no exclusions or alternatives — an agent cannot tell from the description whether get_platform_overview, get_platform_performance, or get_daily_breakdown should be preferred when account-level totals are not what is wanted.

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