sigtap Agent Tools

deliverability_audit

SPF/DKIM/DMARC deliverability audit for a sending domain Free check: https://sigtap-outreach-api.sigtap.workers.dev/preview/deliverability = 200 demo sample, no wallet. Paid call: 402 challenge -> sign -> retry = settled on-chain. ($0.003 USDC on Base, x402)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`domain`	Yes	Domain to audit, e.g. openai.com

Output Schema

TableJSON Schema

Name	Required	Description	Default
`spf`	Yes
`dkim`	Yes
`dmarc`	Yes
`checks`	Yes
`domain`	Yes
`verdict`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "checks": {
+      "type": "object"
+    },
+    "dkim": {
+      "type": "object"
+    },
+    "dmarc": {
+      "type": "object"
+    },
+    "domain": {
+      "type": "string"
+    },
+    "spf": {
+      "type": "object"
+    },
+    "verdict": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "domain",
+    "spf",
+    "dmarc",
+    "dkim",
+    "checks",
+    "verdict"
+  ],
+  "type": "object"
+}

First observedSep 5, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The description discloses that a free check returns a demo sample, and a paid call requires a 402 challenge, signing, and retry, with a cost of $0.003 USDC on Base. This covers primary behaviors and costs, though it does not mention data handling or potential side effects.

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?

The description is concise and follows a logical flow: what it does, then free vs. paid modes. It is slightly run-on but each sentence adds relevant information, with no redundant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since no output schema is provided, the description should clarify the return format or result structure. It only mentions a 'demo sample' for the free check, leaving the full output shape—and error handling—unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'domain' is fully described in the schema with a clear type, requirement, and an example ('openai.com'). The description reinforces that it is the domain to audit, leaving no ambiguity.

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?

Description clearly states the tool performs an SPF/DKIM/DMARC deliverability audit for a sending domain. The verb 'audit' and resource 'sending domain' are specific, but it does not explicitly differentiate from sibling tools like email_grade or domain_age.

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

Usage Guidelines2/5

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

The description explains free vs. paid calling modes but provides no guidance on when to choose this tool over alternatives. It does not mention use cases or conditions that would favor this audit over other email-related tools.

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

All sigtap Agent Tools 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.