Skip to main content
Glama
langmail-mcp

langmail-mcp

Official
by langmail

Mark emails read, to-do or starred

mark_emails

Set or clear read, unread, to-do, and starred flags on messages so you can mark what you read, flag items needing action, and keep or star messages as requested.

Instructions

Set or clear the flags on one or more messages: read / unread, to-do, and starred. Reading a message with get_email, get_thread or search_emails never changes its read state, so call this when the user wants what you read marked read or says "keep this unread"; set todo when a message needs action from the user ("flag this for me", "add it to my to-dos"), clear it when the to-do is done ("mark it done"), and set starred for "star this". Several flags go in one call; a flag you leave out is untouched. To finish a to-do, call this tool with todo: false (plus read: true if it is still unread), then archive_emails. Takes message ids from search_emails or get_thread; folders are untouched, and re-running it on the same ids is harmless. To get a message out of the inbox use archive_emails or move_emails instead; to mark something as spam, use move_emails with Junk. Reports how many messages were marked and lists any id the server refused.

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": {
      "ids": "<ids>"
    },
    "name": "mark_emails"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYesMessage ids to act on (1–50), as returned by search_emails or get_thread. To act on a whole conversation, pass every id get_thread lists.
readNotrue marks the messages read, false marks them unread. Leave out to keep read state.
todoNotrue flags the messages as a to-do for the user, false clears the to-do (e.g. once it is done). Leave out to keep it.
starredNotrue stars the messages, false removes the star. Leave out to keep it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior1/5

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

The description says re-running the tool on the same ids is harmless, which implies idempotent behavior, but the annotations explicitly set idempotentHint=false. This is a direct contradiction, and under the scoring rules a description that contradicts annotations receives a 1 for behavioral transparency.

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?

The description is front-loaded with the core action and then supplies workflows, examples, and alternatives in a dense but readable way. It is somewhat long, but most sentences carry actionable information rather than filler.

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

Completeness4/5

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

For a mutation tool with no output schema, the description covers the important context: flag semantics, combined calls, id sources, folder behavior, alternatives, and return reporting. The only material gap is the idempotency conflict, which undermines confidence in the behavioral disclosure.

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

Parameters4/5

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

Schema coverage is 100%, so each parameter is already documented. The description still adds useful semantics beyond the schema: several flags can be combined in one call, omitted flags are untouched, ids come from search_emails or get_thread, and todo:false plus read:true is the way to finish a to-do before archiving.

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 opens with a specific verb and resource: set or clear read/unread, to-do, and starred flags on one or more messages. It clearly distinguishes this tool from sibling tools such as archive_emails, move_emails, and get_email by naming what those tools do instead.

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 with concrete user phrasings ('keep this unread', 'flag this for me', 'mark it done', 'star this') and explains when not to use it, routing inbox removal to archive_emails or move_emails and spam marking to move_emails with Junk. It also describes the multi-step to-do completion workflow with archive_emails.

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