Skip to main content
Glama

Coline

Send mail

send_mail
Destructive

Writes a new email for the person to approve. It waits in Coline until they send it there; the person sees it here as it will go out. Use it only when they clearly want the email 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>",
      "subject": "<subject>",
      "to": "<to>",
      "body": "<body>"
    },
    "name": "send_mail"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYesComma-separated addresses.
bccNo
bodyYesPlain text.
subjectYes
accountIdYesFrom list_mailboxes.
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

B3.4/5.0
Behavior4/5

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

Adds real context beyond the annotations: the message is held in Coline and the person approves/sends it there, and they see the message as it will go out. This is exactly the kind of state-changing, human-in-the-loop behavior annotations cannot express. It says nothing about retry/idempotency semantics or permission requirements, and the framing sits in mild tension with destructiveHint=true for a tool whose actual send happens elsewhere.

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?

Two short sentences, front-loaded with the core behavior, and no filler. The clause 'the person sees it here as it will go out' is slightly awkward but carries a distinct meaning about preview fidelity.

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?

Return-value detail is covered by the output schema and safety by the annotations, so the remaining burden is workflow and parameters. The approval workflow is handled well, but for a 9-parameter, open-world mutation the description leaves the sender/account prerequisites and the meaning of the retry identifier entirely to the schema.

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?

The description explains no parameters at all, while schema coverage is only 67% across 9 parameters and cc, bcc and subject carry no schema descriptions. With required inputs like workspace, accountId and to, the description should at least note that a mailbox and sendAs address must be resolved first.

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?

States a specific verb and resource ('Writes a new email') and immediately adds the distinguishing behavior that it is queued for human approval rather than sent. An agent can tell this apart from a straight-send tool, though no sibling is named.

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

Usage Guidelines3/5

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

Gives one explicit gating condition ('only when they clearly want the email sent'), which is useful intent guidance, but names no alternative tool to use when the condition fails (e.g. a draft or reply tool) and gives no prerequisites such as having resolved a mailbox first.

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