Skip to main content
Glama

discover_brand_domains

Read-onlyIdempotent

Find all domains belonging to a brand portfolio by aggregating certificate, DNS, redirect, and mail-policy signals from an exact seed domain.

Instructions

Discover all domains that belong to a brand's portfolio by aggregating certificate, DNS, redirect, and mail-policy signals. Use when asked what domains are part of a brand portfolio, or to find all domains related to a brand. Pass the EXACT seed domain verbatim — do NOT normalize or substitute a canonical domain.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domain": "<domain>",
      "discovery_mode": "<discovery_mode>"
    },
    "name": "discover_brand_domains"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNoDiscovery depth. standard is default; deep expands candidate seeding and enrichment fanout.
domainYesSeed domain, used verbatim: never normalize or swap in a canonical domain (clau.de stays clau.de).
formatNoOutput verbosity.
signalsNoSignal modules to invoke. Defaults to all 12 discovery/enrichment signals.
planner_modeNoDiscovery planner: observe emits metrics; enforce applies candidate-backed signal caps.
brand_aliasesNoOptional public brand aliases to seed, such as product or legal-entity labels.
force_refreshNoBypass the cache.
discovery_modeYes"classic" (default) runs the public signal sweep; "tiered" adds private-binding tier lookups first.classic
dkim_selectorsNoOptional DKIM selectors to probe. Defaults to a built-in common-selector list.
min_confidenceNoDrop candidates whose combined confidence falls below this threshold (0-1, default 0.5).
candidate_domainsNoOptional candidate domains supplied by the caller for corroboration.
ownership_verifiedNoAttest you own or may scan the seed domain. Required for "tiered" unless enterprise/owner/partner.

Output Schema

NameRequiredDescriptionDefault
scoreYes
passedYes
partialNo
categoryYes
findingsYes
checkStatusNo
verdictWithheldNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv3.111.2
    • changedInput schema / properties / discovery_mode / description
      Previous value: -"Discovery mode. \"classic\" (default, BSL-licensed) runs the public signal-sweep pipeline. \"tiered\" layers Tier 0 (tenant-declared portfolio), Tier 1 (infrastructure-graph), and Tier 2 (declared-evidence) lookups in front of the legacy sweep, falling back to Tier 3 (the existing sweep) only on cache miss / very_stale fingerprint / uncovered caller candidates. Tiered mode requires private BlackVeil service bindings — BSL self-hosts should leave this on \"classic\"."New value: +"\"classic\" (default) runs the public signal sweep; \"tiered\" adds private-binding tier lookups first."
    • changedInput schema / properties / domain / description
      Previous value: -"The exact seed domain to expand, scanned verbatim (e.g., example.com). Do NOT normalize, resolve, or substitute a brand's canonical/main domain — pass the literal domain the user named (e.g. pass `clau.de`, not `anthropic.com`). Use `brand_aliases` for related brand labels."New value: +"Seed domain, used verbatim: never normalize or swap in a canonical domain (clau.de stays clau.de)."
    • changedInput schema / properties / force_refresh / description
      Previous value: -"Bypass cache and run a fresh check. Useful after DNS changes."New value: +"Bypass the cache."
    • changedInput schema / properties / format / description
      Previous value: -"Output verbosity. Auto-detected if omitted."New value: +"Output verbosity."
    • changedInput schema / properties / ownership_verified / description
      Previous value: -"Caller attests that the seed domain is owned or authorized for scanning. Required when discovery_mode is \"tiered\" and the caller is not an enterprise/owner/partner principal. Prevents unauthorized mass reconnaissance via deep tier lookups."New value: +"Attest you own or may scan the seed domain. Required for \"tiered\" unless enterprise/owner/partner."
    • changedInput schema / properties / planner_mode / description
      Previous value: -"Planner mode for staged discovery fanout. observe emits metrics; enforce applies candidate-backed signal caps."New value: +"Discovery planner: observe emits metrics; enforce applies candidate-backed signal caps."
  2. Changed1 schema field changedv3.103.1
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed1 schema field changedv3.98.1
    • addedOutput schema / properties / verdictWithheld
      Added value: +{
      +  "type": "boolean"
      +}
  4. Changed2 schema fields changedv3.54.0
    • addedOutput schema / properties / checkStatus
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / partial
      Added value: +{
      +  "type": "boolean"
      +}
  5. Addedv3.37.0
  6. Removedv3.31.1
  7. First observedv3.29.7

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds useful mechanism — four signal families are aggregated — plus a concrete input constraint about passing the seed verbatim. It says nothing, however, about latency or whether this call blocks versus the _start/_status job pattern, and no mention of caching despite a force_refresh parameter. Against this sibling set, that missing execution model is a real behavioral gap.

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?

Three sentences, front-loaded with purpose, then usage, then a hard constraint — no filler and nothing buried. It loses a point only because the final sentence largely duplicates the 'used verbatim: never normalize' wording already present in the domain parameter's schema description.

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?

This is a 12-parameter, multi-mode tool (classic vs tiered, standard vs deep, planner modes) with a populated sibling family suggesting an async variant. The description covers what it does and one input rule but omits the execution model, the cost/latency difference between depth and discovery_mode, and the ownership attestation requirement for tiered. The output schema handles return values, so that is not a gap.

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?

Schema description coverage is 100%, so the schema already explains every one of the 12 parameters, including the verbatim-domain rule that the description restates. The description adds no meaning about depth, discovery_mode, signals, min_confidence, or the ownership_verified attestation beyond what the schema says. Baseline 3 applies.

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?

The description opens with a specific verb and resource — 'Discover all domains that belong to a brand's portfolio' — and names the signal classes it aggregates (certificate, DNS, redirect, mail-policy). That is far more specific than the name alone. It never distinguishes itself from siblings such as discover_subdomains or discover_brand_domains_start/_status/_findings, so an agent cannot tell from this text whether it is the synchronous counterpart to the job-based variants.

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: 'Use when asked what domains are part of a brand portfolio, or to find all domains related to a brand.' That is a clear when-to-use statement. It stops short of the alternative side — no guidance on when to prefer discover_subdomains, the _start/_status job flow, or compare_domains, and no prerequisites or cost caveats.

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

Deploy Server

Other Tools