Delete a label

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

Adds real value beyond the destructiveHint/idempotentHint annotations by disclosing the blast radius: messages survive in place, only the tag is lost, and no mail is deleted. What it does not disclose is the gating mechanism implied by "GATED" and the confirmed parameter, nor whether a bare call without confirmation errors or silently proceeds.

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?

Front-loaded with the verb and the reassuring non-destructive-to-mail fact, and it uses dash clauses efficiently. The one-word sentence "GATED." is the only weak spot: it occupies space without conveying a usable instruction unless the reader already knows the convention.

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 destructive mutation, the description covers the safety question (what is and isn't destroyed) and the scope question (labels, not folders), which is the core of what an agent needs. No output schema exists, so some indication of the return/result of a dry_run preview would round it out, as would an explanation of the gating and of why 0 parameters are required.

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 75%, so the baseline is 3. The description reinforces the label/labels mutex in prose, which is a small plus, but it adds nothing about dry_run beyond the schema and completely ignores the undescribed confirmed parameter — the exact parameter "GATED" seems to allude to, making the omission conspicuous.

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?

Specific verb+resource ("Delete a label outright") with an explicit scope boundary: labels only, folders are not deletable here, which cleanly separates it from the folder siblings like list_folders and move_to_folder. The word "outright" hints at entity-level deletion versus the per-message remove_label, but remove_label is never named, so the single most confusable sibling is left to inference.

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?

Gives concrete operational guidance — "Pass label for one or labels for several" — and states a clear exclusion (folders cannot be deleted here), which routes the agent away from folder tools. It stops short of naming remove_label as the alternative for detaching a label from specific messages, and the trailing "GATED" is never unpacked, so the agent is not told that a confirmation step is expected.

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