Skip to main content
Glama

Edit Email Draft

update_draft
Destructive

Edit an unsent email draft by changing only the subject, body, or recipients you provide, then send it with send_draft. Rejects messages that are not drafts.

Instructions

Edit an unsent draft: its subject, body or recipients. Only fields you pass change. Refuses any message that is not a draft. Send it afterward with send_draft.

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": {
      "message_id": "<message_id>"
    },
    "name": "update_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoComma-separated email addresses; replaces the current CC list. Empty string clears it
toNoComma-separated email addresses; replaces the current To list. Empty string clears it
bccNoComma-separated email addresses; replaces the current BCC list. Empty string clears it
bodyNoNew body; replaces the whole body, including any quoted history
mailboxNoEmail address of another mailbox to act on (delegated or shared), e.g. 'someone@example.com'. Omit for your own mailbox; required when this server signs in as an application. Only addresses this server is configured to allow will be accepted.
subjectNoNew subject
message_idYesThe draft's message ID
content_typeNoBody content type: Text or HTML (default: Text)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, but the description adds the crucial partial-update contract ("Only fields you pass change"), which is not derivable from the annotations. It does not warn that body edits overwrite quoted history, though that detail is carried by the schema.

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?

Four short sentences, each earning its place: action, update semantics, precondition, and next step, in that order. Nothing is repeated from the title or schema.

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 8-parameter mutation tool with full schema coverage and no output schema, this covers purpose, partial-update behavior, failure mode, and the natural follow-up call. The mailbox/delegation nuance is left entirely to the schema, which is a minor omission rather than a gap.

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 description coverage is 100%, including replacement vs. clearing semantics for address fields, so the schema does the heavy lifting. The description only echoes the field families (subject, body, recipients) and adds no format or edge-case detail beyond the schema.

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?

States a specific verb+resource ("Edit an unsent draft") and enumerates the editable surface (subject, body, recipients). The phrase "unsent draft" alone distinguishes it from send_draft and delete_draft without opening any 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?

Gives a clear precondition ("Refuses any message that is not a draft") and a follow-up route ("Send it afterward with send_draft"). It does not explicitly point to create_draft for drafts that do not yet exist, but the when-to-use context is unambiguous.

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

Deploy Server

Other Tools