Skip to main content
Glama
mail-mcp-server

mail-mcp-server

plan_send

Preview an email send without changing anything: verify sender, recipients, subject, body, and attachments, then get a plan_id to execute after user approval.

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. Send a draft (draft_id) or a message given here (same fields as create_draft). The summary shows the exact sender, recipients, subject, body and attachments; only execute_plan sends.

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>"
    },
    "name": "plan_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toNoRecipients; for a reply, defaults to the sender being answered
bccNo
bodyNoPlain-text body
fromNoA send-as address of the mailbox; default is its default identity
forwardNoMessage id to forward, with its text and attachments
mailboxYesA connected mailbox address (see list_mailboxes)
subjectNoRequired for a new message; a reply or forward derives Re:/Fwd:
draft_idNo
reply_toNoMessage id being replied to (keeps the thread)
reply_allNoWith reply_to: also copy the other recipients

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, the description carries the full burden and does well: it declares the operation is non-mutating, discloses the return payload (affected items plus a plan_id), and enumerates what the summary contains (sender, recipients, subject, body, attachments). It omits operational details such as plan_id lifetime or single-use semantics and any permission/auth requirements, which keeps it short of a 5.

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 critical fact ('Dry run: changes nothing') is front-loaded and every sentence carries actionable content. The closing clause 'only execute_plan sends' restates the earlier execute_plan reference, a minor redundancy that keeps it from a 5.

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 an 11-parameter tool with no annotations and no output schema, the description covers the essentials: non-mutating behavior, the plan_id handoff, the confirmation UX, and the two input modes (draft_id vs. inline fields). Remaining gaps are edge-case details like plan_id expiry and what happens on validation failure, which are secondary for correct invocation.

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?

Schema coverage is 73%, so the schema already documents most fields; the description's main contribution is framing the parameter set as 'same fields as create_draft' and noting that draft_id selects an existing draft. The mapping of summary contents to from/to/subject/body/attachments adds modest meaning, but it does not clarify the less obvious parameters (reply_to vs. forward, reply_all, from send-as) beyond what the schema says.

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 opening 'Dry run: changes nothing' plus the later 'Send a draft (draft_id) or a message given here' states a specific verb (plan a send) and resource (an email message/draft) precisely. It also explicitly distinguishes itself from the sibling that performs the actual send ('only execute_plan sends'), so an agent can separate the two without opening either schema.

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 names the alternative (execute_plan) and gives a concrete confirmation workflow: show the user the summary, then ask whether to execute. It also tells the agent it may either supply a draft_id or inline message fields matching create_draft. It stops short of explicit exclusions (e.g., when not to plan vs. just create a draft), so it is clear context rather than a full when/when-not rule set.

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