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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds substantial context beyond that: auth requirement, paused-inbox scope, all-or-nothing atomicity, the protected-label set that cannot be modified, and the held-message caveat (body withheld, held label not removed). This is unusually rich behavioral disclosure.

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?

Despite its length, the block is front-loaded (trigger, auth, paused-inbox rationale, inputs) and every subsequent sentence carries a distinct operational fact — constraint, edge case, return shape, or error code. Nothing is redundant 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?

With no output schema, the description supplies the return shape ({object:'list', limit, count, data}, ordered by message_ids) and enumerates the failure modes (400 missing_message_ids, duplicate_message_ids, too_many_ids, missing_labels; invalid_label/protected_label/label_conflict; 404 inbox_not_found). An agent has everything needed to call and interpret it.

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; the description goes further by documenting the cross-field constraint 'At least one of add_labels or remove_labels is required' and the mark-read idiom (remove_labels ["unread"]), neither of which is expressible in the schema. The 1-to-50 unique-id rule is repeated from the schema, adding little.

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?

The opening sentence states a specific verb and resource ('several stored messages should gain or lose the same labels'), immediately distinguishing this batch operation from the singular cooper_update_message sibling. An agent can tell what it does without opening the 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?

It gives a clear triggering condition ('Use this when several stored messages should gain or lose the same labels, including marking a batch read') and an important context constraint ('Works on a paused inbox, because this is triage and not a send'). It does not explicitly name cooper_update_message as the single-message alternative, so the routing is implied rather than spelled out.

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