Skip to main content
Glama

draft

Destructive

Create, update, send, delete, reply, or forward email drafts. Preview drafts before saving and check recipients for restrictions.

Instructions

Full draft lifecycle for review-before-send workflows (destructive: covers send and delete). action=create saves a new draft in the Drafts folder and returns its id (use dryRun: true to preview without saving; checkRecipients: true runs mail-tips first). action=update patches an existing draft by id (only fields passed are changed). action=send dispatches an existing draft — shares the rate limit with send-email. action=delete removes a draft permanently. action=reply/reply-all creates a reply draft from a message id (use comment to prepend text — mutually exclusive with body). action=forward creates a forward draft (requires id and to). Recipient allowlist applies to create/update/forward. Returns the draft object on create/update/reply/forward; status confirmation on send/delete.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform (required)
idNoDraft or message ID. Required for update/send/delete/reply/reply-all/forward.
toNoComma-separated recipient email addresses (optional for create/update, required for forward)
ccNoComma-separated CC email addresses
bccNoComma-separated BCC email addresses
subjectNoEmail subject
bodyNoEmail body (plain text or HTML)
importanceNoEmail importance (default: normal)
commentNoComment text for reply/forward (prepended to original message). Cannot combine with body.
dryRunNoPreview draft without saving (action=create only, default: false)
checkRecipientsNoCheck recipients for out-of-office, delivery restrictions before saving (action=create, default: false)
Behavior5/5

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

Aligns with annotations (destructiveHint: true) by noting send and delete are destructive. Adds behavioral context: rate limit sharing with send-email, dryRun and checkRecipients side effects, and permanent removal on delete. No contradictions.

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?

Single paragraph with good front-loading. Every sentence adds value, though could be slightly restructured (e.g., bullet points) for clarity. Not overly long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers return values outputs for all actions, mentions recipient allowlist and rate limits, and handles all seven actions with 11 parameters. No output schema, but description compensates well.

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

Parameters5/5

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

Schema has 100% coverage but description adds significant meaning: explains dryRun and checkRecipients purpose, notes mutex between comment and body, and specifies when parameters are required. Enhances agent understanding.

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?

Description clearly states 'Full draft lifecycle for review-before-send workflows' and lists all seven actions. It distinguishes from siblings by referencing 'send-email' rate limit and recipient allowlist, clearly defining the tool's scope.

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?

Provides explicit guidance for each action, including required parameters (e.g., id for update/send/delete, to for forward) and constraints (e.g., comment and body mutually exclusive). Does not explicitly state when to use sibling tools like send-email, but implies alternatives through rate limit mention.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/littlebearapps/outlook-assistant'

If you have feedback or need assistance with the MCP directory API, please join our Discord server