Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Send Email

send_email
Destructive

The sending mailbox is resolved automatically from the draft log created by draft_email or draft_reply — no mailbox arg needed. Dict with success status. On a Superhuman mailbox it also carries sent_at, up to a minute ahead of the call — Superhuman holds the message for its Undo Send window and it leaves the outbox then. If the user says a just-sent message hasn't arrived, tell them it lands at sent_at rather than sending it again.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
draft_idYesThe draft_id returned by draft_email or draft_reply. A draft made with on_behalf_of sends with the same on_behalf_of.
providerNoDeprecated and ignored — the mailbox is resolved from the draft log. Omit it.
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. Changed2 schema fields changed
    • changedInput schema / properties / draft_id / description
      Previous value: -"The draft_id returned by draft_email or draft_reply"New value: +"The draft_id returned by draft_email or draft_reply. A draft made with\non_behalf_of sends with the same on_behalf_of."
    • changedInput schema / properties / on_behalf_of / description
      Previous value: -"Send a draft you created on a consented teammate's behalf —\npass the SAME email you passed to draft_reply. The send goes out from\ntheir mailbox. Gated on that teammate's act-on-behalf setting; a\nteammate who hasn't granted it is rejected. Omit to send your own draft.\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": "Send a draft you created on a consented teammate's behalf —\npass the SAME email you passed to draft_reply. The send goes out from\ntheir mailbox. Gated on that teammate's act-on-behalf setting; a\nteammate who hasn't granted it is rejected. Omit to send your own draft."
-}
    • addedInput schema / properties / on_behalf_of
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Send a draft you created on a consented teammate's behalf —\npass the SAME email you passed to draft_reply. The send goes out from\ntheir mailbox. Gated on that teammate's act-on-behalf setting; a\nteammate who hasn't granted it is rejected. Omit to send your own draft.\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

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true, and the description adds context beyond that: the mailbox is auto-resolved (no arg needed), and the returns block discloses the Superhuman Undo Send hold and the incremental sent_at, plus a directive not to re-send a message the user says hasn't arrived. That is meaningful behavioral disclosure the annotations do not carry.

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 purpose and the confirmation gate, then structured with summary/returns tags. The returns prose is somewhat long, but it substitutes for a missing output schema, so most of it earns its place.

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 takes on the burden of explaining the return value (success status, sent_at on Superhuman) and adds the confirmation, mailbox-resolution, and do-not-resend guidance. Nothing an agent needs to invoke this correctly appears to be 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%, so baseline is 3, but the description adds the important framing that the sending mailbox is resolved automatically from the draft log, which explains why provider is deprecated and why no mailbox argument is needed. It is a modest increment over the schema rather than a major one.

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 — 'Send a previously created email draft' — and ties it directly to the draft_email / draft_reply siblings that produced the artifact. An agent can distinguish it from those siblings without opening any schema.

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?

Explicit precondition: 'Only call this AFTER the user has explicitly confirmed they want to send the draft.' It also implies the required prior step (draft creation via draft_email/draft_reply), so both the entry condition and the workflow ordering are stated.

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