Blackveil DNS

brand_audit_single

Read-onlyIdempotent

Audit a single target domain to discover brand-related domains and classify them as consolidated, shadow IT, vendor dependency, or impersonation, revealing brand risk and attack surface.

Instructions

Run a full brand audit on a single target with optional standard/deep discovery depth, brand aliases, and caller-supplied candidate domains. Discovers brand-related domains, looks up registrar + registrant for each candidate, and classifies each into consolidated, real registrar-sprawl shadowIt, authorized vendor dependency, indeterminate, or impersonation relationships. Gated tier-wide by monthly BRAND_AUDIT_QUOTAS (free/agent=0, developer=50, partner=200, enterprise=500, owner=unlimited).

Input Schema

TableJSON Schema

Name	Required	Description
`view`	No	Output view mode. 'registrar_complement' produces a registrar-complement payload; requires enterprise tier. Default 'standard'.
`depth`	No	Discovery depth. standard is default; deep expands candidate seeding and enrichment fanout.
`domain`	Yes	Target domain to audit (e.g., apple.com).
`format`	No	Inline output mode. Defaults to "both".
`planner_mode`	No	Planner mode for staged discovery fanout. observe emits metrics; enforce applies candidate-backed signal caps.
`brand_aliases`	No	Optional public brand aliases to seed, such as product or legal-entity labels.
`force_refresh`	No	Bypass cache and run a fresh check. Useful after DNS changes.
`discovery_mode`	No	Brand-discovery pipeline mode. classic = legacy sweep; tiered = tenant/graph/evidence wrappers first (BlackVeil-internal).
`min_confidence`	No	Drop candidates whose combined confidence falls below this threshold (0-1, default 0.5).
`candidate_domains`	No	Optional candidate domains supplied by the caller for corroboration.
`ownership_verified`	No	Caller attests that the target domain is owned or authorized for scanning. Required when discovery_mode is "tiered" and the caller is not an enterprise/owner/partner principal.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`score`	Yes
`passed`	Yes
`partial`	No
`category`	Yes
`findings`	Yes
`checkStatus`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv3.78.0Sep 9, 2026

changedInput schema / properties / view / description

Previous value: -"Output view mode. 'csc_complement' produces a CSC-tuned payload; requires enterprise tier. Default 'standard'."New value: +"Output view mode. 'registrar_complement' produces a registrar-complement payload; requires enterprise tier. Default 'standard'."

changedInput schema / properties / view / enum

Previous value: -[
-  "standard",
-  "csc_complement"
-]New value: +[
+  "standard",
+  "registrar_complement"
+]

Changed2 schema fields changedv3.54.0Aug 19, 2026
- addedOutput schema / properties / checkStatus
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / partial
```
Added value: +{
+  "type": "boolean"
+}
```
First observedv3.29.7Jul 5, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag safe, read-only, idempotent behavior. The description adds meaningful non-obvious behavior: it discovers domains, performs registrar/registrant lookups, and classifies relationships, and it discloses tier-wide monthly quota gating with exact limits. This exceeds what annotations alone convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three dense sentences with no filler: purpose first, process second, quota gating third. Every sentence earns its place, though 'shadowIt' appears to be a minor spacing typo.

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

Completeness4/5

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

Combined with a rich output schema, full parameter descriptions, and safety annotations, the description covers the tool's purpose, pipeline, classification outcomes, and quota constraints. It does not describe async/report flows or all discovery-mode caveats, but those are largely carried by sibling names and the schema.

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?

All 11 parameters have schema descriptions, so the baseline is 3. The description names depth, brand aliases, and candidate domains but does not add semantic detail beyond the schema; the schema remains the primary source for parameter meaning.

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 specific verb and resource: 'Run a full brand audit on a single target,' and it names optional inputs (depth, aliases, candidate domains) plus the concrete output classification categories. This clearly distinguishes it from discovery-only and batch siblings by emphasizing 'single target' and 'full brand audit.'

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

Usage Guidelines3/5

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

The phrase 'single target' and 'full brand audit' imply this is for one-target comprehensive audits, and the quota note tells when it may be blocked, but no alternatives are named or excluded. There is no explicit guidance on choosing this over brand_audit_batch_start or discover_brand_domains.

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

Deploy Server