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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the '[read-only]' tag and endpoint disclosure add little safety context beyond restating them. The description does usefully reveal that the payload includes nested ad sets and ads and that it wraps GET /api/v2/ads/campaigns, but says nothing about pagination or result limits, which matter for a list 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 compact sentences with the read-only marker front-loaded and the field inventory doing the heavy lifting. The parenthetical endpoint note is small but arguably redundant with the tool name.

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 takes on the burden of describing return values and does so reasonably by listing the fields. However, for a list endpoint it omits pagination, ordering, and result-size behavior, and it does not touch the brandId scoping rules, so an agent could still be surprised at call time.

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 baseline is 3. The description reinforces that status and platform are filters, but never mentions brandId, whose default and 403-on-brand-bound-key semantics are carried entirely by 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 ('List') and resource ('The brand's ad campaigns') and enumerates the returned fields (status, budget, dates, spend, ad sets, ads), so an agent knows exactly what this returns. It does not explicitly distinguish itself from ads_campaign_get (single campaign) or ads_accounts_list, leaving that separation to be inferred from the plural name.

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?

'Filter by status or platform' implies the usage context (surveying campaigns by state or platform), but there is no explicit when-to-use versus ads_campaign_get or ads_insights, and no stated prerequisite about the brand scoping behavior that the brandId schema documents.

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