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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses concrete behavioral limits: 24 groups max without group, 12 ads per page with group, an exact total, and pagination via nextCursor requiring the same arguments. It also flags the important semantic caveat that counts are stored records, not spend or reach — precisely the kind of context annotations cannot convey.

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?

Dense but front-loaded: platform scope first, then kind semantics, then the two-mode behavior, then pagination and the counts caveat. Every sentence adds information an agent needs to construct a call; nothing is repeated from the schema or annotations.

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 fully compensates by describing the shape of both return modes (group list with record counts and first/last observation dates; per-group ad pages with exact totals) plus the pagination contract. For a 6-parameter, two-mode read tool this covers everything needed to invoke it correctly.

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%, so the description must carry the load and does: kind's two enum values are given distinct semantics, group's role as a returned key is spelled out, query is described as a name filter, sort's default and options are stated, and cursor's reuse requirement is explained. Platform's three enum values are named in the opening sentence.

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 verb and resource ('Research advertisers or destination domains on one platform') and immediately defines the two modes via kind=advertiser vs kind=destination, including how grouping keys are derived. It never contrasts itself with sibling tools like search_ads or compare_ads, so an agent cannot fully rule out the alternatives from this text alone.

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 description clearly explains the two-mode usage pattern: omit group to list at most 24 groups, then set group to a returned key to drill into that group's ads, following nextCursor with identical arguments. That is solid in-tool guidance, but no exclusion or comparison against the seven sibling tools (search_ads, compare_ads, get_ad_evidence) is offered, leaving the selection decision implicit.

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