Skip to main content
Glama

Arcangel Trademark Search

Check trademark availability

check_trademark
Read-onlyIdempotent

Check whether a brand, product or company name is available as a trademark. Searches the USPTO register and scores similar marks by conflict risk. Free, no account needed. Signed-in Arcangel users can set full_report for a full clearance search (US + EU/WIPO, dead marks, domains, common-law). Results include a link to file the trademark with Arcangel AI.

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": {
      "mark": "<mark>"
    },
    "name": "check_trademark"
  }
}

Input Schema

NameRequiredDescriptionDefault
markYesThe word mark to check, e.g. "Lumora".
classesNoNice classes (1-45). Use suggest_nice_classes if unsure.
full_reportNoFull clearance report. Requires Sign in with Arcangel.
goods_servicesNoWhat the mark will be used for, e.g. "organic skincare". Improves class matching.

Output Schema

NameRequiredDescriptionDefault
markYes
partYesWhich part of the report this is.
partsYesHow many parts the report has. If part < parts, call get_trademark_check with part + 1.
scopeYesWhat was searched.
reportYes
statusYesrunning: call get_trademark_check with search_id after retry_after_seconds.
verdictYesPlain-language summary of the register findings.
file_urlYesLink to file this mark with Arcangel AI.
conflictsYesClosest conflicts, highest risk first.
search_idYes
signed_inYesWhether the caller is signed in with Arcangel (needed for full reports).
risk_countsYesNumber of conflicting marks per risk level.
highest_riskYes
conflicts_totalYesAll conflicts found, across every part.
retry_after_secondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / properties / conflicts_total
      Added value: +{
      +  "description": "All conflicts found, across every part.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / part
      Added value: +{
      +  "description": "Which part of the report this is.",
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / parts
      Added value: +{
      +  "description": "How many parts the report has. If part < parts, call get_trademark_check with part + 1.",
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "mark",
      -  "status",
      -  "report",
      -  "scope",
      -  "verdict",
      -  "highest_risk",
      -  "risk_counts",
      -  "conflicts",
      -  "search_id",
      -  "retry_after_seconds",
      -  "signed_in",
      -  "file_url"
      -]New value: +[
      +  "mark",
      +  "status",
      +  "report",
      +  "scope",
      +  "verdict",
      +  "highest_risk",
      +  "risk_counts",
      +  "conflicts",
      +  "search_id",
      +  "retry_after_seconds",
      +  "signed_in",
      +  "file_url",
      +  "part",
      +  "parts",
      +  "conflicts_total"
      +]
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "conflicts": {
      +      "description": "Closest conflicts, highest risk first.",
      +      "items": {
      +        "properties": {
      +          "classes": {
      +            "description": "Nice classes, e.g. \"IC 042\".",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "mark": {
      +            "type": "string"
      +          },
      +          "owner": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "register": {
      +            "description": "Source register, e.g. USPTO, EUIPO, WIPO.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "risk": {
      +            "description": "CRITICAL, HIGH, MEDIUM, LOW or INFO.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "serial": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "status": {
      +            "description": "Register status, e.g. REGISTERED or a pending status.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "url": {
      +            "description": "Public record link.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "mark",
      +          "risk",
      +          "status",
      +          "owner",
      +          "classes",
      +          "register",
      +          "serial",
      +          "url"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "file_url": {
      +      "description": "Link to file this mark with Arcangel AI.",
      +      "type": "string"
      +    },
      +    "highest_risk": {
      +      "enum": [
      +        "CRITICAL",
      +        "HIGH",
      +        "MEDIUM",
      +        "LOW",
      +        "INFO",
      +        null
      +      ],
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "mark": {
      +      "type": "string"
      +    },
      +    "report": {
      +      "enum": [
      +        "quick",
      +        "full"
      +      ],
      +      "type": "string"
      +    },
      +    "retry_after_seconds": {
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "risk_counts": {
      +      "additionalProperties": {
      +        "type": "integer"
      +      },
      +      "description": "Number of conflicting marks per risk level.",
      +      "type": "object"
      +    },
      +    "scope": {
      +      "description": "What was searched.",
      +      "type": "string"
      +    },
      +    "search_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "signed_in": {
      +      "description": "Whether the caller is signed in with Arcangel (needed for full reports).",
      +      "type": "boolean"
      +    },
      +    "status": {
      +      "description": "running: call get_trademark_check with search_id after retry_after_seconds.",
      +      "enum": [
      +        "complete",
      +        "running"
      +      ],
      +      "type": "string"
      +    },
      +    "verdict": {
      +      "description": "Plain-language summary of the register findings.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    }
      +  },
      +  "required": [
      +    "mark",
      +    "status",
      +    "report",
      +    "scope",
      +    "verdict",
      +    "highest_risk",
      +    "risk_counts",
      +    "conflicts",
      +    "search_id",
      +    "retry_after_seconds",
      +    "signed_in",
      +    "file_url"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: the data source is the USPTO register, the basic call is free and unauthenticated, full_report requires sign-in and expands coverage, and results include a filing link. It omits latency/pagination and how conflict scores are presented, but the added context is substantial.

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?

Four tight sentences, front-loaded with what the tool does, then cost, then the upsell path. Every sentence carries distinct information; only the trailing filing-link line is marginal.

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?

An output schema exists, so return values need not be explained, and the description still flags what the results contain. Cost, authentication requirements, and the free-vs-full-report tradeoff are all covered for a simple read-only lookup.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema's terse 'Full clearance report' by enumerating what full_report actually returns (US + EU/WIPO, dead marks, domains, common-law), which materially helps an agent decide whether to request it.

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?

States a specific verb and resource (check availability of a word mark) plus the mechanism (USPTO register search with conflict-risk scoring). It does not, however, differentiate itself from the sibling get_trademark_check, which an agent could easily confuse with this tool.

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?

Gives useful context on tiering — free with no account for the basic check, and full_report only for signed-in Arcangel users needing US + EU/WIPO, dead marks, domains and common-law coverage. It never says when to prefer this over get_trademark_check or when suggest_nice_classes is a prerequisite (that routing only appears in the schema).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources