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

Annotations only supply openWorldHint and destructiveHint=false, so the description carries the real burden and does: it discloses that nothing is delivered, that the service rejects a second draft to a recipient with an open one, and — critically — that drafts cannot be deleted from this surface. That last point is an irreversibility fact the annotations do not 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?

Four short sentences, front-loaded with the core guarantee ('UNSENT', 'Nothing is delivered') before the constraints. No sentence is filler; each one closes a distinct failure mode (duplicate draft, undeletable draft).

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?

An output schema exists so return values need no explanation, and the annotations plus description together cover safety, side effects, and preconditions well. The residual gap is parameter-level: with 8 params at 13% description coverage and a misleading empty required list, an agent still has to infer which fields a valid call needs.

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 only 13% across 8 parameters, so the description is expected to compensate, but it names no parameter. Only 'the recipients they named' loosely gestures at to/cc; threadId, agentName, companyId, connectionId, and the body/subject constraints are left entirely to the schema. Note also that the schema reports zero required parameters despite minItems/minLength on to, body, and subject — the description does not resolve that ambiguity.

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 — saves ONE unsent draft into the company's connected mailbox (Gmail or Missive) — and immediately disambiguates from the send path with 'Nothing is delivered.' An agent can tell this apart from connection_send_connected_message without opening either 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 the positive condition ('a draft the member approved in this conversation, with the recipients they named'), the negative condition ('never create one to test the tool'), and the named alternative when the duplicate guard fires ('revise the stored artifact instead'). All three routing questions an agent would ask are answered in-text.

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