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

Goes well beyond the annotations: it discloses the authorization model (drop owner or workspace owner/admin, forbidden otherwise), the validation error with details.code campaign_not_started, the exact effect on unsent people ('stay with their text'), the drain behavior ('moves to sent once nothing is still going out'), and the idempotent result signal ('changed (false when it already was so)'). It also flags untrusted viewer-supplied content in results. Nothing here conflicts with readOnlyHint=false, idempotentHint=true, or destructiveHint=false, since closing is reversible via reopen.

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?

Every sentence carries information, but the delivery is a chain of colon-separated fragments and run-ons with no clear ordering, forcing the reader to parse twice. The verb and the two modes should be front-loaded rather than preceded by an abstract definition of a drop. It is information-dense but poorly structured.

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 two-parameter mutation with no output schema, the description covers permissions, failure modes, state transitions, return fields, and the drop_drafts_off condition. The only ambiguity is whether drop_drafts_off is an error code or a workspace-state note, which a reader must infer. Otherwise an agent has enough 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 coverage is 100%, so the baseline is 3, but the description adds real semantics beyond the schema: it explains what closing actually does to in-flight sends and to people who have not been sent yet, which the one-line schema text does not. The campaignId parameter receives no added explanation, which keeps it from a 5.

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 states the specific action ('closed: true closes a drop that sent', 'closed: false reopens it') and scopes it to personal-email drops. It differentiates from siblings by noting that retry_drop_failed and take_over_drop still work on a closed drop, though it never contrasts with lnkdrp_archive_drop or lnkdrp_delete_drop. The opening framing sentence is dense jargon and buries the verb.

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?

It gives implied context ('closes a drop that sent', stops intake and sending) and a precondition (not-yet-sent drops fail with campaign_not_started). However, it never says when to prefer closing versus archiving, deleting, or leaving a drop running, and the nearest alternative tools are only mentioned as things that still function on a closed drop, not as decision alternatives.

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