Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Draft Reply

draft_reply

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNoOptional list of additional CC recipients. Each is an object with required "email" and optional "name". Example: [{"email": "bob@acme.com"}]
bccNoOptional list of BCC recipients, same format as "cc".
bodyYesReply body in Markdown, rendered to HTML at send time — same rules as draft_email: hyperlinks as [text](url), single newlines preserved as line breaks.
email_idYesThe database id of the email to reply to (from search_emails results)
reply_allNoIf true, reply to all original recipients (Reply All). Default: false (reply to sender only).
on_behalf_ofNoA teammate's email (one with team actions turned on), or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / on_behalf_of / description
      Previous value: -"Draft the reply on a consented teammate's behalf — pass their\nemail. The draft is created in their mailbox; pass the same teammate to\nsend_email to send it. Gated on that teammate's act-on-behalf setting\n(stricter than conversation sharing); a teammate who hasn't granted it is\nrejected. Omit to draft from your own account.\nOr pass an agency client's email, from list_agency_clients, to run the call in that client's account, where none of the teammate limits above apply."New value: +"A teammate's email (one with team actions turned on), or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
  2. Changed2 schema fields changed
    • removedInput schema / properties / as_teammate
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Draft the reply on a consented teammate's behalf — pass their\nemail. The draft is created in their mailbox; pass the same teammate to\nsend_email to send it. Gated on that teammate's act-on-behalf setting\n(stricter than conversation sharing); a teammate who hasn't granted it is\nrejected. Omit to draft from your own account."
-}
    • addedInput schema / properties / on_behalf_of
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Draft the reply on a consented teammate's behalf — pass their\nemail. The draft is created in their mailbox; pass the same teammate to\nsend_email to send it. Gated on that teammate's act-on-behalf setting\n(stricter than conversation sharing); a teammate who hasn't granted it is\nrejected. Omit to draft from your own account.\nOr pass an agency client's email, from list_agency_clients, to run the call in that client's account, where none of the teammate limits above apply."
+}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds the crucial behavioral point that this only stages a draft and must never be sent without user confirmation, which goes beyond the annotations. It also discloses the return dict contents, though it omits details like whether an existing draft gets overwritten or thread-subject handling.

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?

Front-loaded with the core action and workflow in the first lines; the XML-ish summary/returns tags add light structural overhead but every sentence carries actionable content. No filler.

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?

With no output schema, the description supplies the return shape (success, draft_id, provider, original email context), plus the prerequisite tool call and the mandatory confirmation step. An agent has everything needed to invoke it safely.

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 100%, with email_id, body Markdown rendering, reply_all, cc/bcc, and on_behalf_of fully documented in the schema. The description only reinforces email_id sourcing from search_emails and adds nothing about the other parameters, so baseline 3 applies.

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 (create a reply draft) scoped to an existing thread, and names the provider coverage (Outlook or Gmail). It is clearly distinguishable from sibling draft_email (new message) and send_email (dispatch).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly prescribes the workflow: call search_emails first to get the id, pass it here, then present the draft and get confirmation before send_email. This is when-to-use plus a hard guardrail against a harmful alternative.

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

All Sliq 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