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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety is fully covered and the description needn't repeat it. The description adds genuinely useful substance — the exact metric set returned and that scope is account-level or campaign-level. It says nothing about result granularity limits, pagination, date handling, or empty-data behavior, which is a modest gap for a reporting tool.

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?

Two short sentences with the metric list and the usage trigger front-loaded, so an agent can stop reading after the first line. There is mild redundancy: 'day by day' and 'day-by-day' restate the same concept, and the first sentence largely previews the second rather than adding new information.

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 and only three parameters, the description does the important work of enumerating which metrics are returned, which the agent needs since returns are otherwise undefined. Combined with annotations covering the read-only profile and the schema covering two of three params, the definition is sufficient to select and invoke the tool; only the date_preset semantics remain undocumented.

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 67%, so the schema already documents campaign_id and ad_account_id. The phrase 'for the account or a specific campaign' reinforces that campaign_id is an optional narrowing filter while ad_account_id is mandatory, which is a small value-add. The date_preset enum values and their meaning (including whether they are rolling windows) are left entirely to the schema.

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 verb-plus-resource ('Get day-by-day spend, ROAS, CPA, add_to_cart data') and the entity scope ('for the account or a specific campaign'), so the agent knows exactly what data comes back. The 'Meta' qualifier partly separates it from the close sibling get_platform_daily_breakdown, but it never names that sibling to make the distinction explicit.

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 trigger phrasing: 'Use when user asks for a chart, graph, daily trend, or day-by-day analysis,' which is directly actionable for intent matching. It stops short of any exclusion or alternative — it does not say to prefer get_platform_daily_breakdown for non-Meta platforms or get_account_overview for aggregated totals.

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