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

Annotations already declare destructive=true and readOnly=false, and the description meaningfully adds to that: create is explicitly non-sending, send is a 'real send and cannot be recalled', and dry_run:true previews with nothing sent. That is exactly the mutation/irreversibility detail an agent needs. Still silent on permissions and scheduling reversibility for sendAt.

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?

A single dense paragraph that front-loads the resource and then walks the actions in enum order, with no wasted sentences. The 'action list:' / 'get:' pseudo-syntax is slightly awkward but compresses a lot of information efficiently.

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 16-parameter, four-action tool with no output schema, the description covers the decision-relevant behavior of every action, including file attachment on get and the update-by-draftId path on create. What is missing is the shape of list results and pagination behavior, which the absent output schema leaves unanswered.

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 100%, so every one of the 16 parameters is already documented, and the description's per-action framing mirrors that structure rather than extending it. The one real addition is the create-vs-update semantics being restated in prose; otherwise the schema carries the load, making the baseline 3 correct.

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?

Names the concrete resource (the member's unsent drafts in their Connections inbox) and then spells out the four legal actions with a one-line gloss each. An agent can tell what the tool does at a glance; only the relationship to the sibling send tools (email_send, email_sent) is left implicit.

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?

Each action is annotated with the condition that selects it ('create: save a new draft, or update one by draftId', 'send: send a saved draft as it stands'), which is solid per-action routing. It stops short of naming alternatives such as email_send for non-draft mail, so the agent must infer which tool to reach for at the boundary.

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