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

Annotations declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety and idempotency profile is already covered. The description adds only that it operates on 'a saved outgoing message'. With annotations carrying the behavioral burden, the bar is lower, but the description adds no extra context such as whether labels are created on the fly, whether existing labels are replaced, or the effect of passing the same label in both add and remove.

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?

A single, front-loaded sentence with no filler. It is appropriately sized, though it is so terse that it omits useful context rather than being wasteful.

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 in a large sibling family of label-update and update variants, the description is too thin. It omits target-message preconditions, interaction with bulk variants, and the meaning of add/remove when labels overlap, though the existence of an output schema means return values needn't be described. The description does not supply enough context for an agent to confidently choose this tool over its near-identical siblings.

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 0%, but the schema itself is fairly self-documenting: add_labels and remove_labels are named arrays with item constraints (case-sensitive, trimmed, ≤128 UTF-8 bytes, maxItems 32), and message_id is a typed uuid. The description does not explain the add/remove semantics beyond the verb, so it fails to compensate for the low coverage, but the parameter names are intuitive. Baseline 3 is appropriate for good names with no additional semantic detail.

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 description states a specific verb+resource: 'Add or remove labels on a saved outgoing message.' The 'outgoing' qualifier distinguishes it from update_message_labels (received messages) and update_draft. However, it doesn't explicitly name those siblings, so the differentiation relies on the agent mapping 'outgoing' to the sent-message tool family.

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?

There is no guidance on when to use this tool versus update_message_labels, update_thread_labels, update_draft, or the bulk variants. The description implies the operation (label mutation on sent messages) but never states preconditions, such as the message needing to exist and be a sent/outgoing message.

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