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

Goes beyond the annotations by disclosing the side-effect model ('updates QuailOS and mirrors to the IMAP mailbox when the message came from an IMAP account'), the reversibility guarantee ('Nothing is permanently deleted'), and the permission requirement ('Owner/admin read/write AI keys only'). Note: the IMAP mirroring slightly strains openWorldHint=false, though it is the owner's own mailbox so not a true contradiction.

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 sentences, front-loaded with the actions, then behavior, then permission gate. Every sentence carries information, though the parenthetical about QuailOS/IMAP is dense and could be split.

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 mutation tool with no output schema, it covers the key agent questions: what changes, that it is non-destructive, idempotency (via annotations), and who may call it. It stops short of clarifying return/confirmation details, but no output schema exists to absorb that.

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 all 5 parameters including the enum values and the 'folder needed for move' dependency. The description's '(INBOX/ARCHIVE/TRASH/SPAM)' and 'move (needs folder)' merely restate schema content; 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 specific verbs (archive, move, mark read/unread) and the resource (Email Assistant messages), and lists the exact folder set for 'move'. It is trivially distinguishable from read siblings like get_email/list_emails and from the create-oriented send_email/draft_email_reply.

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?

The enumerated actions make the intended usage obvious and 'exactly like the Email Assistant buttons' anchors it, but there is no explicit when-to-use or when-not guidance and no named alternative (e.g., vs get_email or send_email). Usage 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.