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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the write nature is already known. The description adds the crucial non-obvious behavior that a non-partial report prunes adsets missing from the list, which is real destructive semantics beyond the annotations. It stops short of describing return values or error handling.

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?

Front-loads the core action and tokenless constraint, then adds the pruning rule. Dense but every clause carries information; the field enumeration is slightly list-like but useful for matching the payload.

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 nested-object mutation tool with no output schema, the description covers what is mirrored, the profile keying, and the pruning contract. It omits return shape and failure behavior, but the essential call-time semantics are present.

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 50%, and the description compensates by explaining that the adsets array is the cabinet's complete list and that omission prunes entries — meaning the schema alone would not convey. The partial flag's chunking role is left to the schema, and fb_user/ad_account_id are only covered by schema descriptions.

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 (Mirror) and resource (adsets) for one Facebook ad account, enumerates the mirrored fields, and explicitly contrasts the tokenless path with the Graph-token approach. It also names the sibling register_meta_cabinet it completes, so an agent can place it in the campaign → adset → ad tree without opening the schema.

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?

Gives clear context: it runs on every cost sync and lands under the same tokenless Meta profile as register_meta_cabinet, implying it should follow cabinet registration. It does not explicitly exclude or route against report_meta_ads or report_meta_ad_stats, so the when-not guidance is incomplete.

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