Delete a Gmail user label while keeping existing conversations intact. Requires confirm=true to authorize this destructive action.
Delete a user label (Gmail settings -> Manage labels). Conversations keep existing without it.
Requires confirm=true (outward-facing or destructive).
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Exact name of the user label to delete. | |
| confirm | No | Must be true: this action is outward-facing or destructive. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It usefully discloses the blast radius (conversations survive, only the label is removed) and the confirm=true gate, but says nothing about reversibility, whether deletion fails if the label is missing, or permission requirements — all material for a destructive tool.
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?
Two short sentences, zero waste, with the core action and consequence front-loaded and the confirm precondition second. Nothing could be cut without losing information.
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 two-parameter, no-output-schema delete tool with no annotations, the description covers the action, the side-effect scope, and the safety gate. The remaining gaps (error behavior for a nonexistent label, reversibility) are real but secondary.
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 100%, so both parameters are already documented. The description only restates the confirm requirement already present in the schema and adds no new semantics for `name` (e.g., case sensitivity, exact-match behavior, or what happens on a partial name).
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 ("Delete a user label") and clarifies the effect on conversations, which separates it from gmail_label (assignment) and gmail_labels (listing). It never names a sibling or an alternative route, so it stops short of full differentiation.
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?
Usage is implied by the verb and by the stated confirm gate, but there is no explicit "use this when..." or "use gmail_label instead when you only want to remove the label from messages". The agent must infer the boundary from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.