List Saved Drafts

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds value beyond that by disclosing the required scope (mailbox.read), the sort order (newest first), and the cursor-based pagination contract.

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 short sentences, zero filler, with the purpose and ordering front-loaded before the permission and pagination notes. Every sentence carries information an agent would otherwise have to infer.

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 read-only paginated list tool with full schema coverage, an output schema, and rich annotations, this covers scope, auth, ordering and pagination. Only the routing to sibling tools for draft detail or message listing is left implicit.

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 limit, cursor and mailbox_id are already fully documented, and the baseline of 3 applies. The description only adds the soft heuristic "use a small limit," without clarifying cursor lifetime, stability across pages, or mailbox_id omission behavior beyond what the schema states.

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 ("List saved drafts") plus scope ("in the selected inbox") and ordering ("newest first"). It does not name a sibling such as mailbox_get_draft or mailbox_list_messages to disambiguate draft-listing from message-listing, so it stops short of a 5.

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?

Provides real usage context: the required scope mailbox.read and explicit pagination advice ("Use a small limit and continue with the returned cursor"). It gives no when-not guidance or named alternative for cases where the caller wants full message listings instead.

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