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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds meaningful context beyond that: separate metadata and performance date windows, reliance on an exact-account reader being enabled and complete, and the restriction that this is observation only with no efficiency conclusions. This helps an agent understand limitations without contradicting the annotations.

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 description is short and contains no filler, but the first sentence is a dense, jargon-heavy run-on that packs in 'campaignMetadataAsOf,' 'publication-qualified,' and 'mature attribution facts' without unpacking them. It would benefit from breaking the content into clearer, more readable clauses, so it is not well-structured enough for a 4.

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, so the description carries the burden of explaining what gets returned; it does qualitatively list campaign config and performance facts. Still, key terms like 'publication-qualified,' 'mature attribution,' and 'exact-account reader' are left undefined, and there is no mention of pagination behavior or how the three parameters shape the result set beyond what the schema already states.

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 100%, with all three parameters (sort, limit, state) already documented in the input schema. The description adds no parameter-level detail, but it does not need to because the schema fully handles semantics; this is the appropriate 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?

The description identifies the resource as Amazon Ads campaign identity/configuration and enumerates the included performance facts (spend, orders, ACoS, ROAS), so an agent can infer it returns campaign data. However, it lacks an explicit verb like 'list' or 'get' and does not clearly distinguish itself from the sibling get_campaign_detail, which is likely the singular-detail counterpart.

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?

The only usage-related signal is the conditional 'when its exact-account reader is enabled and complete,' which is more of a data-availability caveat than guidance on when to select this tool over siblings. It does not mention alternatives such as get_campaign_detail or find_campaign, nor does it state when a caller should prefer list-style retrieval over detail lookup.

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