Email header analyzer: SPF/DKIM/DMARC/ARC verdicts, domain alignment, hop delays. No lookups.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlapping purpose. Its scope (raw header analysis, read-only, no network calls) is clearly stated and unambiguous.
The single tool name analyze_headers follows a clear verb_noun snake_case convention. With only one name there is no inconsistency possible, and it is descriptive of its action and target.
A single tool is slightly thin for the stated domain, though it is a comprehensive analyzer rather than a trivial stub. The narrow, single-purpose read-only scope justifies one entry point, but batch or record-verification variants could reasonably exist.
The tool covers the core header-analysis lifecycle well: alignment, SPF/DKIM/DMARC/ARC verdicts, hop chain, and explained findings. Minor gaps remain (no DNS/record lookup or signature verification, no batch or export), but these are workarounds rather than dead ends.
Analyze pasted raw email headers. Reports From / Return-Path / Reply-To / DKIM d= alignment (relaxed and strict), SPF / DKIM / DMARC / ARC verdicts as recorded by the receiving servers (Authentication-Results, ARC-*), the Received hop chain oldest first with per-hop delays and public IPs, and plain-English findings with severity and what each means or how to fix it. Makes no network or DNS calls and does not verify signatures. Header text is not stored. Read-only. Same engine as the MailAlign JSON API (POST /api/analyze).
| Name | Required | Description | Default |
|---|---|---|---|
| headers | Yes | The full raw header block of one email, e.g. "Received: from ... Authentication-Results: ... From: ...". A body after the first blank line is ignored. | |
| include_raw | No | Also return the full /api/analyze JSON (all findings and hops) in structuredContent.raw. |
| Name | Required | Description |
|---|---|---|
| arc | No | |
| raw | No | Full /api/analyze response (only when include_raw is true) |
| spf | No | |
| dkim | No | |
| hops | Yes | |
| dmarc | No | |
| verdict | Yes | |
| version | Yes | |
| findings | Yes | |
| publicIps | No | |
| fromDomain | No | |
| spfAligned | No | |
| dkimAligned | No | |
| hopsOmitted | No | |
| findingsOmitted | No | |
| totalDelaySeconds | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: it makes no network or DNS calls, does not verify signatures, and does not store header text. These are exactly the operational facts an agent needs before routing sensitive email content here.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core action, then a dense but useful enumeration of outputs and constraints. Slightly long, and the MailAlign API cross-reference is arguably incidental, but every clause carries information an agent can act on.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter read-only analysis tool with a full output schema and complete annotation coverage, nothing material is missing: inputs, outputs, side effects, and safety profile are all addressed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already well documented, including the body-after-blank-line behavior and the include_raw semantics. The description adds no parameter-level detail (e.g. it never mentions include_raw), so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (analyze) and resource (raw email headers), and enumerates precisely what is reported: alignment, SPF/DKIM/DMARC/ARC verdicts, hop chain, and findings. No siblings exist, and the scope is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes the input condition explicit ('pasted raw email headers') and draws clear negative boundaries ('makes no network or DNS calls and does not verify signatures'), which tells an agent when this tool is and isn't the right fit. It does not state an alternative route, but no sibling tools exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_headersEmail deliverability checks: SPF, DKIM, DMARC, BIMI, MTA-STS, blacklists, headers, spam words
Check a domain's email authentication: SPF, DKIM, DMARC, BIMI, MX, MTA-STS, TLS-RPT. Score + fixes.
Read your own DMARC aggregate and forensic reports: sources, alignment, alerts, CSV export.
Domain checks: SPF, DKIM, DMARC, BIMI, MTA-STS, SSL/TLS and HTTP security headers.
Add one secure layer between your agents and this server.
