tw-patent-mcp

gpss_search

Read-onlyIdempotent

Search Taiwan IPO GPSS patent records by field-code conditions, status, kind, database scope, and pagination; request bibliographic, abstract, or claim output fields.

Instructions

智慧局 GPSS 檢索。conditions 是 {欄位代碼: 條件}，例如 {"TI/AB": "固態電池 or solid state battery", "AX": "台灣積體電路", "ID": "20200101:"}；欄位代碼前加 + 表示跨欄位 OR、加 - 表示 NOT。databases 例如 ["TWA","TWB"]，空＝全部 23 庫。status：A 公開／B 公告；kind：I 發明／M 新型／D 設計。output 預設 PN,ID,AN,AD,TI,PA,IN,IC,AB，要請求項加 CL。

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": {
      "conditions": "<conditions>"
    },
    "name": "gpss_search"
  }
}

Input Schema

Name	Required	Description	Default
`qty`	No
`kind`	No
`skip`	No
`output`	No
`status`	No
`databases`	No
`conditions`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 20, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds real value by explaining the query language (field codes, + for cross-field OR, - for NOT) and default output fields, though it says nothing about pagination behavior for qty/skip.

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?

Very dense and compact, front-loading the core purpose then walking through each parameter. Nearly every clause earns its place; only the unaddressed pagination params leave a gap in an otherwise efficient structure.

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?

For a complex nested-object search tool, the description supplies the query DSL and field-code conventions that the bare schema lacks. With an output schema present, return values need not be explained. The main omission is coverage of qty/skip pagination.

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 0%, so the description carries the burden. It thoroughly explains conditions syntax with examples, databases (empty = all 23), status (A/B), kind (I/M/D), and output defaults including CL for claims. It omits qty and skip (pagination) meaning, leaving two params 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?

States a specific verb+resource: GPSS search (檢索) against TIPO patent databases. An agent can tell it is a query tool. It does not explicitly distinguish itself from siblings like gpss_get or gpss_codes, so it falls short of the top score.

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 by the mechanics (supply conditions to search), but there is no explicit statement of when to use this versus gpss_get or gpss_codes, nor any prerequisites or exclusions. The agent must infer routing from the sibling names.

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

Deploy Server