tw-patent-mcp

ops_search

Read-onlyIdempotent

Search global patent bibliographic data using EPO OPS CQL queries, returning up to 100 flattened results per call or raw JSON.

Instructions

EPO OPS CQL 檢索（全球書目）。例：'ti=battery and pa=tsmc'、'pn=TW201644272'、'ipc=H01M10 and pd within "2022 2024"'。constituent 可為 biblio（含書目）或 abstract。一次最多 100 筆。預設回壓平的命中清單，raw=true 回原始 JSON。

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": {
      "cql": "<cql>"
    },
    "name": "ops_search"
  }
}

Input Schema

Name	Required	Description	Default
`cql`	Yes
`end`	No
`raw`	No
`start`	No
`constituent`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.2.0Oct 23, 2026

addedInput schema / properties / raw

Added value: +{
+  "default": false,
+  "title": "Raw",
+  "type": "boolean"
+}

First observedv0.1.0Oct 20, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: a hard cap of 100 hits per request and a choice between a flattened hit list (default) and raw JSON (raw=true). It omits OPS throttling/quota behavior, which would matter for a global open-world search.

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?

Dense and front-loaded: the tool's identity comes first, then query examples, then the result-shape and limit behavior. The CQL examples are long but earn their space by teaching syntax; nothing is redundant filler.

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?

An output schema exists, so return values need not be spelled out, and the flattened-vs-raw note is a useful addition. But for a 5-parameter search tool with 0% schema description coverage, the absence of any pagination (start/end) or quota guidance leaves a genuine gap in what an agent needs to call it correctly.

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 0% across 5 params, so the description must compensate. It does add meaning for `cql` (syntax + examples), `constituent` (biblio vs abstract), and `raw` (flattened vs raw JSON), but says nothing about `start`/`end` semantics or defaults, leaving pagination undocumented.

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 names a specific verb+resource: EPO OPS CQL search over global bibliographic data, with concrete CQL query examples ('ti=battery and pa=tsmc', 'pn=TW201644272'). It does not, however, distinguish itself from siblings like ops_biblio or ops_fulltext, so an agent must infer that this is the free-form query entry point rather than a record-retrieval 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?

Usage is implied through worked CQL examples and the note that `constituent` can be biblio or abstract, which shows how to shape a query. There is no explicit when-to-use/when-not guidance and no mention of when an agent should prefer ops_biblio, ops_family, or ops_fulltext instead of a CQL search.

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

Deploy Server