Skip to main content
Glama

Arcangel Trademark Search

Get a trademark check result

get_trademark_check
Read-onlyIdempotent

Get the result of a trademark check that was still running, or the next part of a long full report. Pass the search_id that check_trademark returned, and part when the report says it continues.

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": {
      "search_id": "<search_id>"
    },
    "name": "get_trademark_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
partNoWhich part of a long full report to return. Defaults to 1.
search_idYes

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. Changed5 schema fields changed
    • addedInput schema / properties / part
      Added value: +{
      +  "description": "Which part of a long full report to return. Defaults to 1.",
      +  "maximum": 50,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • 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

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful behavior beyond them: this is a polling/resumption endpoint, and the 'part' mechanism is driven by a continuation signal in the prior report. It omits edge behavior such as how long a search_id stays valid or what is returned if the check is still running.

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?

Two tight sentences with no filler; the dual retrieval purpose is front-loaded and the parameter guidance follows immediately. Every clause carries information an agent needs to call it correctly.

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?

An output schema exists, so return values need not be described. For a 2-parameter read tool, the description covers provenance of search_id, the polling case, and the pagination case. It could say one more thing about what happens when the check is still incomplete, but the essential calling information is present.

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 only 50% — search_id carries no schema description — so the description must compensate, and it does by explaining that search_id comes from check_trademark's return value. It also explains 'part' as driven by the report's continuation signal, adding meaning beyond the schema's min/max/default. Minor gap: it doesn't say what part 1 versus higher parts contain.

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 ('Get the result of a trademark check') and explicitly scopes it to two cases: a check that was still running, or the next part of a long report. It implicitly differentiates itself from check_trademark by describing this as the retrieval half of that pair, though it never names check_trademark as the alternative to avoid.

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?

Gives clear trigger conditions: call this when a prior check was still running, or when the report says it continues. The prerequisite ('Pass the search_id that check_trademark returned') is stated explicitly. It stops short of an explicit when-not, e.g. that a fresh search must start with check_trademark rather than here.

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