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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description adds substantially more: that this call never performs the write itself, the exact return shape on the first call (status='confirmation_required', action_id, plan_token), and the gating tool confirm_action. It also discloses idempotent-by-name behavior, which is real behavioral context an agent cannot get from the schema.

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, front-loaded with purpose, then the deduplication rule, then the confirmation contract. Every sentence carries information; only minor tightening would improve it.

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 non-destructive write with three params and no output schema, the critical missing piece — that the write is deferred behind confirm_action — is fully covered, along with duplicate-name behavior. The gap is the undocumented mailbox parameter, which affects whether the label lands in the right scope.

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 33% — only color carries a schema description. The description compensates for the required name parameter by explaining the re-use/idempotency semantics, which is meaningful. However, mailbox is left entirely unexplained in both schema and description, and color is not expanded beyond the schema's own note.

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 gives a concrete verb+resource ("Make a new label to file mail under") plus an idempotency rule, so the agent knows exactly what the tool produces. It does not distinguish itself from near-name siblings such as mail_label or mail_list_labels, leaving that differentiation to the caller.

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 clearly states the re-use case (existing name returns that label instead of duplicating) and spells out the mandatory two-step flow: call this, receive status='confirmation_required' with action_id and plan_token, then invoke confirm_action. It stops short of naming mail_list_labels as the way to pre-check existing labels, so guidance is clear but not fully comparative.

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