Skip to main content
Glama

Coline

Reply to mail

reply_to_mail
Destructive

Writes a reply in an existing thread for the person to approve; it waits in Coline until they send it. Read the thread first. Use it only when they clearly want the reply sent.

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": {
      "workspace": "<workspace>",
      "accountId": "<accountId>",
      "threadId": "<threadId>",
      "to": "<to>",
      "body": "<body>"
    },
    "name": "reply_to_mail"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYesComma-separated addresses.
bccNo
bodyYesPlain text.
subjectNo
threadIdYesThread id from list_mail_threads or search_mail.
accountIdYesMail account id from list_mailboxes or a thread.
workspaceYesWorkspace slug from workspaces.list, e.g. "acme".
fromAddressIdNoA sendAs address from list_mailboxes, for that exact sender.
clientRequestIdNoA stable id for this message; reuse it on a retry so it isn't held twice.

Output Schema

NameRequiredDescriptionDefault
toYes
fromYes
stateYes
sendIdYes
statusYes
messageYesNever say the mail was sent unless status is sent.
subjectYes
approvalUrlYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true; the description adds the meaningful context that nothing is actually sent — the reply waits in Coline for approval — which softens the destructive profile and tells the agent about the approval workflow. It does not mention permissions, rate limits, or what happens to the thread on success, leaving some gaps.

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

Conciseness5/5

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

Three short sentences with zero waste: what it does, the prerequisite, and the selection condition, with the approval behavior front-loaded. Nothing needs to be cut or moved.

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?

An output schema exists and annotations cover the safety profile, so the description needs only workflow context — which it supplies via the draft/approval model and the read-first prerequisite. Missing only an explicit pointer to the direct-send alternative for the case where approval is not wanted.

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

Parameters3/5

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

With 10 parameters at 70% schema coverage, the schema documents the key fields (threadId, accountId, workspace, fromAddressId, clientRequestId retry semantics) and the description adds nothing beyond them. Fields like cc/bcc/subject are undocumented in both places, but the description's silence is acceptable given the generally strong schema.

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

Purpose4/5

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

The description names a specific verb and resource ('Writes a reply in an existing thread') and adds the crucial qualifier that the result is a draft awaiting the user's approval. It implicitly separates itself from a direct-send tool, but never names an alternative sibling such as send_mail, so the differentiation is behavioral rather than explicit.

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

Usage Guidelines4/5

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

It gives a concrete prerequisite ('Read the thread first') and an explicit gating condition ('Use it only when they clearly want the reply sent'), which tells the agent when to use it and when not to. It stops short of naming the alternative tool to use when the user does not want a reply sent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources