Skip to main content
Glama

Ptab Search Appeals

ptab_search_appeals
Read-onlyIdempotent

Search USPTO ex parte Appeals decisions, an applicant's appeal of a patent examiner's rejection to the Patent Trial and Appeal Board. This is a SEPARATE docket from AIA trials (IPR/PGR/CBM/derivation): an appeal number looks like "2024-001234", not "IPR2024-00001". Returns an outcome-count summary first (affirmed / reversed / affirmed-in-part / other), then the matching decision records, each with the applicant/real-party-in-interest, application and patent number, counsel, art unit, appeal filing date, decision type/date, and the decision document link. Filter by appeal_number, application_number (the rejected application under appeal), free-text query, and/or a decided_after/decided_before date range. Powered by the USPTO Open Data Portal (data.uspto.gov).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "appeal_number": "2024-001234"
    },
    "name": "ptab_search_appeals"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of decision records to return (1-100, default 25). Outcome counts are computed over this same page.
queryNoOptional free-text keyword search across appeal decision records (e.g. a technology term or applicant name).
offsetNoPagination offset (default 0).
_apiKeyNoUSPTO ODP API key (same key as the patents/uspto-ptab packs). Get free at https://data.uspto.gov/apis/getting-started.
include_rawNoOptional, default false. When true, also return raw_sample: one UNMODIFIED raw record exactly as the upstream API returned it (no field renaming), to verify or correct this tool's field mapping.
appeal_numberNoOptional. Ex parte appeal number, e.g. "2024-001234" (with or without an "Appeal" prefix). This is NOT an AIA trial number.
decided_afterNoOptional. Only decisions on/after this date (ISO YYYY-MM-DD).
decided_beforeNoOptional. Only decisions on/before this date (ISO YYYY-MM-DD).
application_numberNoOptional. The patent application number under appeal, e.g. "16123456".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
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 description is free to add substantive behavior instead of repeating safety claims. It does that well: it discloses the two-part return shape (outcome-count summary first, then decision records), enumerates the fields returned, and names the upstream source. It omits that those outcome counts are scoped to the current page (buried in the schema) and says nothing about rate limits or pagination behavior for large result sets.

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?

Sentences are front-loaded: purpose, then dataset boundary, then return shape, then filters, then provenance. Every sentence carries information an agent needs, though the return-field enumeration is a long list and the final provenance line is the lowest-value piece.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Nine optional parameters, no output schema, and no required fields make the description the main source of orientation, and it covers purpose, exclusion, return structure, filterable fields, and data source. Combined with a fully documented schema, an agent has enough to select and call this correctly.

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 description coverage is 100%, so a 3 is the baseline. The description goes further by clarifying the semantics of the two most confusable parameters—`appeal_number` as an ex parte appeal number explicitly not an AIA trial number, and `application_number` as the rejected application under appeal—and by summarizing which filters can be combined.

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 a specific verb and resource ('Search USPTO ex parte Appeals decisions') and immediately draws the boundary against a confusable dataset: 'This is a SEPARATE docket from AIA trials (IPR/PGR/CBM/derivation)', complete with contrasting number formats. An agent can distinguish this from the PTAB trial tools without opening any schema.

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?

It gives a clear when-to-use condition (ex parte appeal of an examiner's rejection) and an explicit when-not ('not IPR/PGR/CBM/derivation'), plus the canonical identifier shape '2024-001234' versus 'IPR2024-00001'. It stops short of naming the specific sibling tool to use for AIA trials, which is the only thing separating this from a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.