Skip to main content
Glama

trademark_text_search

按目标国家查询 One1 已覆盖的商标数据,检索品牌名的音/形/义近似候选。

用于卖家给产品起品牌名前,查是否与已注册商标冲突。
query: 要核查的品牌名或商标词,例如 "Nike"。
nice_class: 尼斯商品类别号(如 "025"=服装鞋帽),可选;提供则按同类目重排风险等级。
live_only: 仅返回有效(Live)注册,默认 False。
limit: 返回条数,默认 10。
⚠️ 判读规则(重要):`count` 是返回的**最近邻条数**,受 limit 上限限制,**不是冲突数**——
即使该词完全无人注册,仍可能返回低风险邻居。判断有无冲突请看 `has_conflicts` /
`conflict_count`(= 风险等级为「高」的条数)。
⚠️ `coverage.clearance_ok` 为 false 时,「无冲突」**不代表可注册**,必须结合当地检索。

返回: {query, conflict_count, has_conflicts, count, results:[...], coverage:{...}}。

country: 单个国家/地区代码,不是任意 ISO 代码;去首尾空白并转大写。省略、空串或纯空白默认 US。英国使用 UK,欧盟 EU,马德里国际注册 WO;不接受多国列表。文本本地配置支持:AR, AT, AU, AZ, BR, CA, CL, CN, CZ, DZ, EE, ES, EU, FI, FR, GE, HR, ID, IE, IL, IN, IT, JP, KH, KR, LT, MX, NO, NZ, PL, PT, PY, RO, SG, SK, TW, UA, UK, US, VN, WO。实际文本检索合作方路由为 BX/DE/ES/IT/TR;BX 未列入覆盖快照,覆盖未验证。编号/权利人工具仅查本地源,能力与文本检索不同。历史图形接口还接受 USPAT 等设计库代码,返回专利图形候选,不代表商标国家覆盖。图形以 coverage_info 的 graphic_served 和实际后端可用性为准,可能有 ARIPO/OAPI 等地区代码。 先调用 coverage_info(country="") 获取覆盖清单,再以目标代码查询各国覆盖。全表来自静态快照,单国优先后端、失败回落静态;注意 warning、scope 和 clearance_ok(工具输出不含数据截止日字段,需要截止日请让用户查 https://one1.cn/api/coverage?country=XX)。各国数据范围、截止时间和完整性不同,多国支持不等于全球全量覆盖;无命中不等于可注册或不侵权。coverage.clearance_ok=false 时不能给可注册结论;true 也不是法律保证。count 是返回数量(文本近似检索为邻居数量),不是冲突数;结合 has_conflicts、conflict_count 和逐条风险信号判断。visual_similarity 不是侵权概率。TRO/enforcement 是库内信号,需核对来源和时间。USPTO/TSDR 仅适用于美国记录,其他国家核对相应官方来源。US 请求仅为示例。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
countryNo单个国家/地区代码,不是任意 ISO 代码;去首尾空白并转大写。省略、空串或纯空白默认 US。英国使用 UK,欧盟 EU,马德里国际注册 WO;不接受多国列表。文本本地配置支持:AR, AT, AU, AZ, BR, CA, CL, CN, CZ, DZ, EE, ES, EU, FI, FR, GE, HR, ID, IE, IL, IN, IT, JP, KH, KR, LT, MX, NO, NZ, PL, PT, PY, RO, SG, SK, TW, UA, UK, US, VN, WO。实际文本检索合作方路由为 BX/DE/ES/IT/TR;BX 未列入覆盖快照,覆盖未验证。编号/权利人工具仅查本地源,能力与文本检索不同。历史图形接口还接受 USPAT 等设计库代码,返回专利图形候选,不代表商标国家覆盖。图形以 coverage_info 的 graphic_served 和实际后端可用性为准,可能有 ARIPO/OAPI 等地区代码。US
live_onlyNo
nice_classNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / country / description
      Added value: +"单个国家/地区代码,不是任意 ISO 代码;去首尾空白并转大写。省略、空串或纯空白默认 US。英国使用 UK,欧盟 EU,马德里国际注册 WO;不接受多国列表。文本本地配置支持:AR, AT, AU, AZ, BR, CA, CN, CZ, DZ, ES, EU, FI, FR, GE, HR, ID, IE, IL, IN, IT, JP, KR, MX, NO, NZ, PL, PT, PY, RO, SG, SK, TW, UA, UK, US, VN, WO。实际文本检索合作方路由为 BX/DE/ES/IT/TR;BX 未列入覆盖快照,覆盖未验证。编号/权利人工具仅查本地源,能力与文本检索不同。历史图形接口还接受 USPAT 等设计库代码,返回专利图形候选,不代表商标国家覆盖。图形以 coverage_info 的 graphic_served 和实际后端可用性为准,可能有 ARIPO/OAPI 等地区代码。"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose substantial behavior: count is neighbor count bounded by limit, not conflict count; has_conflicts/conflict_count are the real signal; coverage.clearance_ok=false invalidates a 'no conflict' conclusion; data comes from a static snapshot with per-country scope/recency differences and no cutoff-date field. It omits auth/permission and read-only/rate-limit traits, which keeps it below 5.

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

Conciseness3/5

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

Front-loaded enough with clear ⚠️ markers, but the reading-rule caveat about count vs. conflict_count is stated twice, and a large block of country-routing lore (BX/DE/ES/IT/TR, USPAT, ARIPO/OAPI) duplicates the schema's country description and is tangential. Noticeably bloated for the information delivered.

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?

No output schema or annotations exist, so the description supplies a return shape ({query, conflict_count, has_conflicts, count, results, coverage}) and extensive caveats about interpreting coverage and counts. For a 5-parameter search tool this is nearly complete; the remaining gap is the absence of auth/permission and rate-limit context.

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 description coverage is only 20% (just country), so the description must compensate and largely does: query is the brand/trademark term, nice_class is the Nice classification with an effect on risk re-ranking, live_only limits to Live registrations (default False), and limit is the result count (default 10). It adds meaning beyond the schema defaults, though examples are thin for nice_class format beyond '025'.

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 states a specific verb+resource (query One1's covered trademark data by target country, retrieve phonetic/visual/meaning-similarity candidates for a brand name) and frames the use case (sellers checking for conflict before naming a product). It also distinguishes itself from siblings by noting that serial-number and owner tools query only local sources and that the graphic interface returns different candidates.

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 a clear context (use before naming a brand to check conflict) and a prerequisite workflow (call coverage_info first, then query per country). It does not explicitly state when to prefer graphic_trademark_search or the owner/serial tools instead, so exclusions are only partially covered.

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.