Skip to main content
Glama
mail-mcp-server

mail-mcp-server

plan_delete_label

Preview deleting a label without touching its messages, returning a plan_id and summary for approval before execution.

Instructions

Dry run: changes nothing. Returns what would be affected and a plan_id for execute_plan. Show the user the summary before asking whether to execute. Delete a user label; its messages stay, without it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mailbox": "<mailbox>",
      "label": "<label>"
    },
    "name": "plan_delete_label"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelYes
mailboxYesA connected mailbox address (see list_mailboxes)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose the key behaviors: nothing is mutated, it returns an affected-items summary plus a plan_id, and the label's messages are preserved rather than deleted. It stops short of covering error cases (e.g., nonexistent label) or permission requirements, and doesn't restate the plan_id's lifetime/validity, so it is strong but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the dry-run guarantee, which is the most decision-relevant fact. "Dry run: changes nothing" is mildly redundant with itself, but otherwise every sentence carries useful information for an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema, the description covers the return shape (affected items + plan_id) and the safety model, which is the important part. It leaves a real gap around how the label identifier is obtained and what the result looks like if nothing matches, which matters given the complete absence of annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%: mailbox carries a description (connected address, see list_mailboxes) while label has none. The description adds no parameter meaning at all — it doesn't say whether label is an ID or a name, how to discover valid labels, or whether matching is case-sensitive — so it fails to compensate for the undocumented required parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Delete a user label") and immediately scopes the effect ("its messages stay, without it"), which tells an agent exactly what is and isn't removed. It also distinguishes itself from the execution sibling by naming execute_plan and framing itself as a dry run.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance (dry run first, present the summary, then ask the user before executing) and names the alternative tool, execute_plan, along with the plan_id handoff. There is no ambiguity about which tool performs the actual deletion.

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