Skip to main content
Glama
lzinga

US Government Open Data MCP

by lzinga

uspto_search_applications

Read-onlyIdempotent

Search USPTO patent applications with flexible queries: boolean, wildcards, exact phrases, field filters, and date ranges. Retrieve recent applications or narrow by filing date, status, and more.

Instructions

Search USPTO patent applications using ODP query syntax (POST). The q param supports opensearch DSL: boolean (AND/OR/NOT), wildcards (* ?), exact phrases (""), field:value, ranges ([from TO to]), comparisons (>=600). Filters narrow results by field value. Range filters narrow by date/number range. All params are optional -- an empty search returns recent applications.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSearch query - e.g. 'applicationMetaData.applicationTypeLabelName:Utility', 'applicationNumberText:14412875', free text 'machine learning', or 'applicationMetaData.filingDate:[2024-01-01 TO 2024-12-31]'
sortNoSort as 'field order' - e.g. 'applicationMetaData.filingDate desc'. Default: filingDate desc. Text fields cannot be sorted.
limitNoResults per page (default 25)
facetsNoFields to aggregate - e.g. ['applicationMetaData.applicationTypeLabelName', 'applicationMetaData.applicationStatusCode']. Text fields not supported.
fieldsNoFields to include in response - e.g. ['applicationNumberText', 'applicationMetaData.patentNumber', 'applicationMetaData.filingDate']. Omit for all fields. Supports wildcards like '*Date*'.
offsetNoStarting position (default 0)
filtersNoArray of filters as 'field value1,value2' strings - e.g. ['applicationMetaData.applicationTypeCode UTL,DES', 'applicationMetaData.entityStatusData.businessEntityStatusCategory Small']. Each entry adds an AND-combined filter; multiple values within a filter act as OR.
range_filtersNoArray of range filters as 'field from:to' strings - e.g. ['applicationMetaData.grantDate 2020-01-01:2024-12-31', 'applicationMetaData.applicationStatusCode 150:200']. Valid for date and number fields only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2026.9.14
    • addedInput schema / properties / limit / default
      Added value: +25
  2. Changed1 schema field changedv2026.4.11
    • removedInput schema / additionalProperties
      Removed value: -false
  3. First observedv2026.3.9

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds behavioral details beyond annotations: it mentions the POST method, the supported DSL operators, and that an empty search returns recent applications. This provides useful context without contradicting annotations.

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 concise and well-structured. It front-loads the purpose and method, then breaks down the query syntax and parameter behaviors in a logical order. Every sentence adds value, and there is no unnecessary fluff.

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 tool with 8 optional parameters and no output schema, the description covers the query syntax, filters, range filters, and optionality. It does not explicitly state the response format (e.g., that it returns a list of applications), but this is largely implied by 'search' and the presence of pagination params. Minor gap but not critical.

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% with detailed descriptions and examples for each parameter. The description adds extra meaning by explaining the q parameter's DSL syntax (boolean, wildcards, phrases, ranges, comparisons) and clarifying that filters narrow by field value while range filters narrow by date/number. This supplements the schema and helps agents construct valid queries.

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 the specific verb 'Search', the resource 'USPTO patent applications', and the query method (POST with ODP syntax). It clearly distinguishes this tool from sibling tools like uspto_application_details by indicating it is a search operation rather than a detail lookup.

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 implies when to use it (for searching applications) and notes that all parameters are optional, returning recent applications on empty search. It doesn't explicitly contrast with sibling tools (e.g., uspto_application_details), but the purpose is clear enough that an agent can infer it is the search tool rather than a detail fetcher.

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

Deploy Server

Other Tools