检索药品专利（rs_drug_patents，2.7 万条）：申请号、标题、法律状态、届满日、申请人。year_from / year_to 按届满年份比较。
| Name | Required | Description | Default |
|---|---|---|---|
| drug | No | 药品名 | |
| limit | No | 返回条数，默认 20，硬上限 20（超出自动压低） | |
| fields | No | 列裁剪，取值见返回列名；默认给摘要列 | |
| offset | No | 翻页偏移，默认 0；offset+limit 不得超过 1000 | |
| status | No | 法律状态关键词 | |
| company | No | 企业或申请人 | |
| year_to | No | 届满年截止 | |
| year_from | No | 届满年起始 | |
| ingredient | No | 成分名 |
Changes observed during successful MCP inspections.
Input schema / properties / limit / descriptionPrevious value: -"返回条数，默认 20，硬上限 50（超出自动压低）"New value: +"返回条数，默认 20，硬上限 20（超出自动压低）"Input schema / properties / offset / descriptionPrevious value: -"翻页偏移，默认 0"New value: +"翻页偏移，默认 0；offset+limit 不得超过 1000"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full behavioral burden. It usefully discloses the dataset size (~27,000 records) and a non-obvious semantic that year_from/year_to filter on expiry year rather than filing year, but says nothing about result limits, pagination behavior, or access requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences with the resource and source-table context front-loaded; no padding or redundancy. It is appropriately sized for what it attempts.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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 is the sole context carrier, and for a 9-param all-optional search returning a known field set it is reasonably complete. The main omission is routing the agent to get_patent_detail for full records.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description restates the field list and the expiry-year comparison, which the schema already conveys in each parameter's own description, so it adds little beyond structured data.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (检索/search) and resource (药品专利/drug patents), and names the underlying source table and record volume (rs_drug_patents, 2.7万条) plus the returned fields. The search-vs-detail distinction against get_patent_detail is implied by the name but never stated explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_patent_detail, nor on prerequisites or sensible query combinations. The description only lists what fields exist, leaving selection entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.