FranklyMail Agentic Inbox

create_mailbox_draft

Save a real plain-text or HTML draft in the mailbox Drafts folder, visible in Apple Mail, webmail and IMAP. Never sends or schedules. Use only at user request. Reuse requestKey only for an identical retry. If saving or unknown, check Drafts instead of creating another copy. Returns draft ID, version, mailboxEmailId and mailboxBlobId.

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": {
      "mailboxId": "<mailboxId>",
      "requestKey": "<requestKey>",
      "to": "<to>",
      "subject": "<subject>",
      "text": "<text>"
    },
    "name": "create_mailbox_draft"
  }
}

Input Schema

Name	Required	Description
`cc`	No
`to`	Yes
`html`	No	Optional HTML formatting: paragraphs, links, emphasis, lists and quotes. Sanitized; no CSS, images, scripts or attachments. Read returned content and warnings. On updates omission preserves existing HTML; provide both bodies when editing, or null to switch to plain text.
`text`	Yes	Required plain-text alternative. Keep its meaning consistent with html.
`subject`	Yes
`mailboxId`	Yes
`requestKey`	Yes
`replyToMessageId`	No
`senderIdentityId`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond annotations by disclosing that nothing is sent or scheduled, that requestKey is a per-request idempotency token for identical retries, that a duplicate copy must not be created on unknown outcomes, and what identifiers come back (draft ID, version, mailboxEmailId, mailboxBlobId). This is the behavioral context a caller needs for a non-readOnly, non-idempotent mutation.

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?

Five short sentences, front-loaded with what the tool produces and what it never does, followed by retry and duplicate-avoidance rules and the return shape. No filler or restatement of the tool name.

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 nine-parameter mutation with no output schema, the description covers safety (no send/schedule), retry semantics, duplicate handling, and return values. The remaining gap is identity/routing parameters (senderIdentityId, replyToMessageId, mailboxId) whose meaning appears in neither the schema nor the description.

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 only 22% (only html and text are documented), so the description must carry more weight; it does explain requestKey precisely and names the return identifiers. It adds nothing for mailboxId, senderIdentityId, replyToMessageId, to, cc, and subject, leaving the majority of the nine parameters semantically opaque.

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 and resource ('Save a real plain-text or HTML draft in the mailbox Drafts folder') and scopes it with 'visible in Apple Mail, webmail and IMAP'. The phrase 'real ... draft' implicitly separates it from prepare_draft/revise_draft siblings, and 'Never sends or schedules' separates it from the scheduled-message tools.

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 explicit conditions: 'Use only at user request', 'Reuse requestKey only for an identical retry', and a recovery path ('If saving or unknown, check Drafts instead of creating another copy'). It never names the concrete alternatives (prepare_draft, update_mailbox_draft, revise_draft), so the agent must infer which sibling fits a non-final draft flow.

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

All FranklyMail Agentic Inbox tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?