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

Goes well past the destructiveHint/idempotentHint annotations: it discloses the always-on confirmation prompt regardless of connection settings, that failed recipients are requeued one at a time seconds apart, that ownership and Gmail sender switch to the taker, and enumerates the exact refusal codes with details fields. This is the level of disclosure a destructive, open-world mutation needs.

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?

Content is dense and front-loaded with the definition before the behavior and refusals, and every clause carries information. The first sentence is an overlong run-on that could be split, and the 'what is a drop' preamble is bulk an agent revisits on every call.

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?

Despite no output schema, the description names the return value (the drop and retried), covers permission gating, the confirmation requirement, requeue timing, all failure modes with remediation hints, and adds an untrusted-content warning for author-supplied text. Nothing an agent needs to call this correctly is absent.

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% and each parameter is well documented there, so the baseline is 3. The description explains the confirmation preview flow that gives confirm/confirmationToken their purpose, but never names or elaborates on the parameters themselves.

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 the specific operation (owner/admin takes over a sent drop whose owner left the workspace) and defines what a drop is, including the crucial 'a campaign in the API' alias that distinguishes it from the sibling lnkdrp_take_over_campaign. An agent can tell exactly what resource is affected and what happens to it.

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?

Preconditions are explicit: caller must be workspace owner/admin, the drop must have been sent, and its owner must have left the workspace. It doesn't explicitly route the agent away from related tools like lnkdrp_retry_drop_failed for the same failed recipients, so the alternatives comparison is implied rather than stated.

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