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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces that ('nothing is ever changed in Meta'). It adds genuinely non-structured behavior: units (amounts are hundredths of the account currency, rates are fractions) and data provenance (visits/engaged visits/time-on-site joined from utm_term, plus a wasted flag). It does not disclose row limits, pagination, or latency, which keeps it below 5.

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 resource and its dimensions, then usage, then units. Dense but every clause carries information; the long first sentence is the only mild readability cost.

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 returns, and it does so by listing the breakdown dimensions, the joined site metrics, and the currency/rate units. Missing are result size, ordering, or pagination behavior, which an agent would want for a multi-dimension breakdown query.

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%, so the schema already documents app, range, source, and environment thoroughly, including enum meanings and defaults. The description adds only indirect context (currency comes from the ad account, placement keyed via utm_term) and never clarifies parameter behavior itself, so the 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 first sentence names a specific verb+resource (Meta ad spend and clicks) and enumerates the exact breakdown dimensions returned: placement, publisher platform, device, country, age, gender. It is clearly distinguishable from get_meta_ads_overview and get_breakdown by naming Meta-specific dimensions, though it never explicitly contrasts itself with those siblings.

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?

'Use it to decide which placements to exclude' gives one concrete decision context, which is more than nothing. But there is no when-not guidance, no mention of get_meta_ads_overview or get_breakdown as alternatives, and no prerequisites (e.g. requiring a connected Meta ad account) beyond the parameter defaults.

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