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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the operational detail: results are sorted by spend and capped at 500 rows. That row cap is exactly the kind of limit an agent needs and cannot get from annotations. It does not describe what happens when the cap is exceeded or how the sorting tie-breaks.

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?

A single front-loaded sentence with no filler; the scope, filter convention, ordering and row cap all appear up front. The dense parenthetical is slightly compressed but every clause carries 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?

For a 10-parameter, all-optional reporting tool with no output schema, the description covers the core dimensions and the row limit. It leaves out date format expectations, valid provider values, and what the default behavior is when no filters are supplied, which an agent would need to call it confidently.

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% across 10 parameters, so the description must compensate. It does partially: the parenthetical explains that website, account and customer filters accept either an id or a uuid, which disambiguates six of the ten parameters. But since/until formats, provider values, and campaign_key semantics are left entirely undocumented.

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?

States a specific resource and granularity: ad performance broken out per provider campaign over a date range. The '[read]' prefix plus 'sorted by spend' makes clear it is a reporting read, and 'per provider campaign' distinguishes it from siblings like ads_insights_summary, ads_insights_timeseries and ads_insights_websites. It stops short of naming those siblings explicitly.

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 by the scope phrase 'for a date range' and the listed filter dimensions. There is no statement of when to prefer this over ads_insights_summary or ads_insights_timeseries, and no mention of prerequisites or defaults when dates are omitted.

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