Skip to main content
Glama

google_patents

Search patent records across Google Patents with advanced filters for inventor, assignee, date, country, language, status, type, and litigation.

Instructions

Searches patent records across Google Patents with advanced filtering by inventor, assignee, date range, country, language, status, type, and litigation status. [Credits: 5 API credits per request] Notes: Pagination uses page (0-indexed) plus num for page size. patent_id values returned (e.g. patent/US7520532B2/en) are the format needed - note this differs slightly from the plain publication_number format (e.g. US7520532B2) expected by google_patent_details' patent_id parameter; strip the 'patent/' prefix and '/en' suffix when passing to google_patent_details. Returns: { organic_results: [ { position, patent_id, title, priority_date, filing_date, grant_date, inventor, assignee, publication_number } ] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
numNoNumber of results to scrape, between 1 and 100. (default: 10)
dupsNoDeduplication method: default is by Family. Available value: language (deduplicate by Publication).
pageNoPage number of results. 0 = first page, 1 = second page, etc. (default: 0)
sortNoSorting method. Default is Relevance. Allowed: new (Newest), old (Oldest). For patents, sorting is by filing date; for scholar results, by publication date.
typeNoFilter by patent type. Allowed: PATENT (Patent), DESIGN (Design).
afterNoMinimum date for results, format type:YYYYMMDD where type is priority, filing, or publication. Example: publication:20230101.
queryYesSearch query. Multiple search terms can be separated with a semicolon (;). Example single term: (Coffee) OR (Tea). Example multi-term: (Coffee) OR (Tea);(A47J). See 'About Google Patents' for advanced syntax.
beforeNoMaximum date for results, format type:YYYYMMDD where type is priority, filing, or publication. Example: priority:20221231.
statusNoFilter by patent status. Allowed: GRANT (Grant), APPLICATION (Application).
countryNoFilter by country code(s). Separate multiple codes with a comma. Example: WO,US.
patentsNoWhether to include Google Patents results. (default: true)
scholarNoWhether to include Google Scholar results. (default: false)
assigneeNoFilter by assignee(s). Separate multiple assignees with a comma.
inventorNoFilter by inventor(s). Separate multiple inventors with a comma.
languageNoFilter by language(s), comma-separated. Supported: ENGLISH, GERMAN, CHINESE, FRENCH, SPANISH, ARABIC, JAPANESE, KOREAN, PORTUGUESE, RUSSIAN, ITALIAN, DUTCH, SWEDISH, FINNISH, NORWEGIAN, DANISH.
clusteredNoHow results should be grouped. Available option: true (Classification).
litigationNoFilter by litigation status. Allowed: YES (Has Related Litigation), NO (No Known Litigation).
Behavior4/5

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

With no annotations, the description fully discloses credits, pagination behavior, patent_id format, and return structure. It does not mention rate limits or error handling, but provides sufficient behavioral details for an AI agent to use the tool correctly.

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?

The description is well-structured: main purpose in first sentence, credits, then key behavioral notes, return format. Every sentence adds value without redundancy. It is front-loaded with essential information.

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?

Given 17 parameters, no output schema, the description covers return structure and key behavioral notes. It explains how to use results with a sibling tool, but could mention more about error states or edge cases for completeness.

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 100%, so the baseline is 3. The description adds significant value by explaining date format (type:YYYYMMDD), semicolon usage for multiple query terms, and the patent_id format conversion, which are not fully covered in the schema descriptions.

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 clearly states the tool searches patent records across Google Patents with advanced filtering, specifying the verb (Searches) and resource (patent records). It differentiates from sibling tool google_patent_details by noting the patent_id format difference and how to pass parameters to that tool.

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?

The description provides context on pagination, date format, and how to use results with google_patent_details, but does not explicitly state when to use this tool versus alternatives like google_scholar or other search tools. The context is clear but lacks explicit exclusions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/alessandrobenigni/ScrapingDog-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server