Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Get Mailbox Deliverability

get_mailbox_deliverability
Read-only

Call this when the user asks why their emails land in spam or the junk folder, or before launching a campaign to confirm the sending mailbox is configured to deliver. Each mailbox reflects the last DNS check — Sliq re-checks daily and on connect, so the data is current without asking the user to re-run it.

verdict is the worst of the four record statuses: 'fail' (a record is misconfigured and may block or junk sends, so is_send_ready is False), 'warn' (advisory — delivery still works), or 'pass' (all four clean). score is a 0-100 roll-up that score_tier buckets into 'good' / 'needs_work' / 'critical'. Each checks entry carries the per-record diagnostic (what is wrong) and fix_instruction_markdown (how to fix it, null when that record passes) — relay these when the user wants to fix a failing record. A mailbox's deliverability is None when it has never been checked — tell the user to open that mailbox in Settings and run the DNS check. An empty mailboxes list means no email account is connected. { 'mailboxes': [ { 'email': str, 'provider': str, 'is_default': bool, 'deliverability': { 'domain': str, 'verdict': 'pass' | 'warn' | 'fail', 'score': int, 'score_tier': 'good' | 'needs_work' | 'critical', 'is_send_ready': bool, 'last_checked_at': str, # ISO 8601 'dns_provider': str, 'checks': [ {'record_type': 'spf' | 'dkim' | 'dmarc' | 'mx', 'status': 'pass' | 'warn' | 'fail', 'raw_record': str, 'diagnostic': str, 'fix_instruction_markdown': str | None}, ... ], }, }, ... ], }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
on_behalf_ofNoAn agency client's email, from list_agency_clients, to run this call in that client's 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
    • addedInput schema / properties / on_behalf_of
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses freshness behavior ('Sliq re-checks daily and on connect, so the data is current without asking the user to re-run it'), null-state handling for never-checked mailboxes, and empty-list meaning. It also explains what the per-record diagnostic and fix_instruction_markdown fields are for and when they are null.

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?

Well front-loaded with the purpose and trigger conditions, and the structured <returns> block keeps return-shape detail out of the prose. It is dense and somewhat long, but nearly every sentence carries distinct information an agent needs (verdict semantics, fix relaying, null handling).

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 formal output schema, the description compensates fully by inlining the return structure and defining every verdict, score_tier, is_send_ready, and checks field, plus the two degenerate states (deliverability=None, empty mailboxes). An agent has everything needed to call and interpret the result.

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?

The single parameter (on_behalf_of) has 100% schema description coverage, so the schema already carries its full meaning. The description adds nothing about acting on behalf of an agency client, 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?

The description opens with a precise verb+resource statement ('Read the DNS deliverability verdict (SPF, DKIM, DMARC, MX) for each connected mailbox'), naming the exact data domain and scope. No sibling tool covers deliverability, and the field breakdown immediately tells an agent what this returns.

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 gives explicit trigger conditions: 'Call this when the user asks why their emails land in spam or the junk folder, or before launching a campaign.' This is clear context for invocation, though it names no exclusions or alternative tools (there are none obvious in the sibling list, so the omission is minor).

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