Skip to main content
Glama
Sign In

Emailchaser

by com.emailchaser
OverviewDiscussionsAdmin

Send AI reply draft

send_reply_draft
Destructive

Sends an AI reply draft to the prospect through the conversation's sender mailbox; it is scheduled for delivery right away and cannot be recalled. The draft's CURRENT subject and body are what goes out, so check its wording before sending: an edit has to be made before it is sent. Refused with 409 for anything that is not a sendable AI reply draft (already sent or scheduled emails, inbound replies, sequence templates) and with 422 when the conversation has no connected sender mailbox or no resolvable recipient.

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": {
      "id": "<id>"
    },
    "name": "send_reply_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe numeric reply draft ID (from list_reply_drafts)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructive=true and idempotent=false, yet the description still adds material context: delivery is scheduled immediately, the send cannot be recalled, the draft's current subject and body are what goes out, and specific 409/422 failure semantics are given. This is exactly the irreversibility and state information an agent needs before invoking a destructive send.

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?

Two dense sentences, front-loaded with the action and irreversibility warning before the error conditions. The clause 'check its wording before sending: an edit has to be made before it is sent' restates the same point twice, which is the only wasted wording in an otherwise tight definition.

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?

For a one-parameter destructive send with no output schema, the description covers everything that matters: what is sent, that it is irreversible and immediate, the required draft state, and the two failure modes. Nothing an agent needs to call this correctly is missing.

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% and the single id parameter is already documented as coming from list_reply_drafts, so the schema does the heavy lifting. The description still adds value by constraining which IDs are valid — anything that is not a sendable AI reply draft is rejected with 409 — which tells the agent more about the identifier's domain than the schema's numeric bounds do.

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 specific verb and resource: 'Sends an AI reply draft to the prospect through the conversation's sender mailbox.' The qualifier 'AI reply draft' and the enumeration of non-sendable types (already sent/scheduled emails, inbound replies, sequence templates) make it distinguishable from the sibling send_reply, which handles ordinary replies rather than drafts.

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?

It clearly states the precondition ('check its wording before sending: an edit has to be made before it is sent') and the conditions under which the call fails (409 for non-sendable drafts, 422 for no sender mailbox or recipient). It does not explicitly name update_reply_draft as the tool to use for the pre-send edit, leaving the agent to infer the sibling, but the implied workflow is unambiguous.

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

All Emailchaser toolsInspect
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