Skip to main content
Glama

Keep a message for later

save_compose_draft

Writes down a message being prepared, so it can be finished later from anywhere. Pass "from" to start one; pass its id to write into it again, where the fields you leave out keep the value they had. Saving sends nothing: send_email is what sends.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "save_compose_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoWho else receives it, in copy. Everyone on the mail sees these.
toNoWho it is written to.
bccNoWho else receives it without the others being told. A blind copy is kept on the sending alone: the thread records the visible recipients only.
bodyNoThe text of the message, as the contact will read it. Plain text, in their language.
fromNoThe address it will be sent from: a mailbox or helpdesk address of the account, or one of the aliases of a mailbox, as list_sender_addresses gives them. Needed to start a message, ignored afterwards.
subjectNoThe subject line, up to 255 characters.
draft_idNoThe id of the unsent message, as list_compose_drafts gives it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / from / description
      Previous value: -"The address it will be sent from, from list_sender_addresses. Needed to start a message, ignored afterwards."New value: +"The address it will be sent from: a mailbox or helpdesk address of the account, or one of the aliases of a mailbox, as list_sender_addresses gives them. Needed to start a message, ignored afterwards."
  2. First observed

TDQS

A4.6/5.0
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 discloses that saving is non-sending, that updates are partial ('fields you leave out keep the value they had'), and that 'from' is only needed on creation and ignored afterwards. It stops short of permissions or draft ownership/visibility rules, which would round it out for a mutation tool.

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, front-loaded with the purpose, then the two calling modes, then the crucial 'does not send' caveat. No filler and nothing buried.

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 7-parameter mutation tool with no annotations and no output schema, the description covers the behavior an agent needs to call it correctly. The one gap is that it never says what comes back (presumably a draft id), which matters since 'draft_id' is the handle for later updates.

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 the baseline is 3, but the description adds real semantics the schema does not: the create-vs-update role of 'from' versus 'draft_id' and the merge behavior for omitted fields. That is meaningful meaning beyond the per-field descriptions.

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 concrete verb and resource ('Writes down a message being prepared') and immediately names the sibling it is not ('send_email is what sends'), so an agent can separate drafting from sending without reading 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 Guidelines5/5

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

It gives explicit branching guidance: pass 'from' to start a draft, pass 'draft_id' to write into an existing one, and it states plainly that saving sends nothing while send_email does. That covers both the when-to-use and the main alternative in the sibling set.

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