FranklyMail Agentic Inbox

update_mailbox_draft

Destructive

Replace a mailbox draft created by this connection. Pass current version and mailboxBlobId as blobId from get_draft. Rejects external edits and scheduled messages. Preserves the old copy in Trash. Never sends. Read warnings about uncertain writes or duplicate copies.

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": {
      "draftId": "<draftId>",
      "version": "<version>",
      "blobId": "<blobId>",
      "to": "<to>",
      "subject": "<subject>",
      "text": "<text>"
    },
    "name": "update_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.
`blobId`	Yes
`draftId`	Yes
`subject`	Yes
`version`	Yes
`senderIdentityId`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the annotations (destructiveHint=true, idempotentHint=false) it discloses behaviors the agent could not otherwise predict: stale version/blobId causes rejection, scheduled messages are refused, the prior copy survives in Trash, the tool never sends, and callers must read warnings about uncertain writes or duplicate copies. That is exactly the concurrency and recovery context a non-idempotent mutator needs.

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?

Six short sentences, each carrying distinct information: identity, prerequisites, rejection rules, side effects, safety guarantee, and post-call obligations. The most decision-critical facts (replace semantics, version/blobId source) are front-loaded with no padding or repetition of the 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 a 9-parameter destructive mutation with no output schema and thin schema documentation, the description covers safety, concurrency, and recovery well and tells the agent to inspect the response for warnings. It falls short on full-replace vs partial-update semantics for cc and on the role of senderIdentityId, which an agent must guess from the required-field list.

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 only 22%, so the description has to carry more weight. It does add crucial meaning for two undocumented parameters — blobId actually derives from mailboxBlobId, and version is used for optimistic-concurrency enforcement — but it is silent on senderIdentityId and says nothing about whether cc is replaced or preserved when omitted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Replace a mailbox draft created by this connection" gives a specific verb (Replace) and resource (mailbox draft) with an ownership scope that rules out drafts made elsewhere. It does not name the nearest siblings (revise_draft, create_mailbox_draft, prepare_draft), so the boundary must be inferred from the scope clause rather than stated.

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?

The description gives concrete preconditions and routing: pass the current version and the mailboxBlobId as blobId, obtained from get_draft, and it explicitly excludes external edits and scheduled messages from eligibility. Clear context, but it never says when to pick this over revise_draft or prepare_draft, which is the remaining ambiguity for an agent.

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?