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

Annotations cover the safety profile, but the description adds substantive behavior: verification by reading flags back off the server so failed changes are named rather than assumed, the no-op-is-not-an-error idempotency semantics, and the non-interference guarantee (stays flagged, answered, in place). This is exactly the extra context beyond structured fields that earns a high score.

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?

Six dense sentences, each load-bearing: purpose, relationship to mark_read, batching instruction, verification behavior, mailbox rule, idempotency, non-interference. The single-call directive is front-loaded and no sentence is 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?

No output schema exists, so the description carries return behavior, and it does: the server verifies flags and names any message it could not change. Combined with the idempotency and scope statements, an agent has everything needed to invoke this correctly.

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 coverage is 100% so the baseline is 3, and the schema already explains batching and UID sourcing. The description adds genuine meaning by explaining *why* `mailbox` matters (a uid is only meaningful in its originating folder), which the schema's 'IMAP folder name. Defaults to INBOX.' does not convey.

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 (mark messages unread) plus the exact semantic scope: restoring the pre-read state, and explicitly the inverse of mark_read. An agent can distinguish this from mark_read, flag_email and unflag_email without opening any 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?

Explicit when-to-use ('the undo for mark_read', 'when a triage pass marked more than the person meant'), how to batch ('pass the whole set in ONE call'), and a conditional routing rule: pass `mailbox` when the uids did not come from INBOX. Alternatives and the exclusion condition are both named.

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