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

Annotations already cover the read-only/idempotent profile, and the description adds genuinely new behavior: metrics appear only 'where available', currencies are never mixed and totals are per currency, and do_not_touch means autopilot will not modify the campaign. It still says nothing about aggregation granularity or pagination.

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?

Core subject and metric list are front-loaded in a single dense sentence with no filler. The parenthetical explaining do_not_touch earns its place, though the sentence is long enough to be mildly run-on.

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 does the work of listing return fields, which it does well. However it never states whether results are a daily series or aggregated over the from/to range, nor whether there is pagination — a meaningful gap for an agent constructing a report.

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 site_id, from and to are already documented with formats and defaults. The description adds no date-range or site-scoping meaning beyond that, which lands at the baseline.

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?

Names the resource (ads data by platform, account, campaign for a site) and enumerates the exact metrics returned, which is far more specific than a restatement of the name. It does not explicitly distinguish itself from near-neighbours like get_site_metrics or get_social, so it stops short of a 5.

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?

Usage is only implied: an agent can infer this is the tool for paid-ad performance reporting, but there is no statement of when to prefer it over get_site_metrics or get_social, and no exclusions or prerequisites. Adequate but relies on inference.

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