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

Annotations carry only destructiveHint=true; the description adds the concrete reason — send=true dispatches a real email immediately and send_at schedules it — which is exactly the behavioral disclosure an agent needs to avoid an accidental send. It omits auth/permission requirements and what is returned, so not a full 5.

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?

Three tight sentences with the highest-risk information (the send warning) front-loaded, followed by threading guidance and the API endpoint. No filler.

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 13-param mutation tool with no output schema, the description covers the critical destructive behavior and threading; the remaining parameter detail is fully carried by the schema. Minor gaps around required sender/organization prerequisites and the returned draft identifier keep it from 5.

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 the schema already documents every parameter, including the send/send_at warnings and the conversation threading field. The description largely restates that, adding no format or syntax detail beyond it; baseline 3 applies.

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 ('Create a draft email/message') and immediately clarifies the scope distinction that matters most: draft-save versus actually sending. An agent can tell this apart from the list_* siblings at a glance.

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 actionable context: use `conversation` to attach to an existing thread, and use send/send_at only when you intend a real send. It stops short of naming alternatives or stating when-not to use it (e.g., replying vs new draft), but the conditional guidance is clear.

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