Skip to main content
Glama

Patent PreCheck

by io.github.Patent-PreCheck
OverviewDiscussionsAdmin

Patent PreCheck — score patentability

precheck_score

Run a patentability pre-check on source code or an invention description. Returns a 0–100 patentability score across the four USPTO statutory pillars (§101 eligibility, §102 novelty, §103 non-obviousness, §101 utility), a separate §112 filing-readiness signal, the band (Not Ready → File Ready), the pillar that holds the band back, top opportunities to strengthen, and a count of prior-art matches consulted. Pass the text to analyze inline via code.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesThe source code or invention description to analyze (>= 10 chars).
tierNoAnalysis tier. Defaults to free; paid tiers require server-side entitlement.
filenameNoOptional filename hint (e.g. main.ts) used for language/context.
invention_kindNoOptional invention category. Sets language and scoring prompts. Prior-art math still follows the disclosure.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / invention_kind
      Added value: +{
+  "description": "Optional invention category. Sets language and scoring prompts. Prior-art math still follows the disclosure.",
+  "enum": [
+    "software",
+    "physical",
+    "process",
+    "unsure"
+  ],
+  "type": "string"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

No annotations are present, so the description carries the behavioral burden. It does this well by enumerating what is evaluated (four statutory pillars plus §112), what is returned, and that prior art is consulted. It does not explicitly disclose side effects, rate limits, or auth requirements, but the operation is clearly an analysis-and-return tool rather than a mutation.

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?

The description is one dense sentence, but every clause adds either a deliverable or an input constraint. It is front-loaded with the action and resource, though a bulleted output list would improve scannability.

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?

With no output schema, the description spells out the full return surface (score, band, blocking pillar, opportunities, prior-art count), so an agent can interpret results. It does not orient the agent among the many siblings, but that gap is primarily a usage-guidance issue rather than an invocation-completeness issue.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents all four parameters. The description adds only the inline-via-code nuance and the phrase 'source code or invention description' for `code`; it does not add meaning for `tier`, `filename`, or `invention_kind` beyond what the schema already provides.

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 names a concrete verb ('Run'), a specific resource ('patentability pre-check on source code or an invention description'), and a detailed output contract (score, §112 signal, band, opportunities, prior-art count). This clearly differentiates it from sibling tools like precheck_compare_to_patent or precheck_cpc_suggest by the overall scoring function.

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?

The intended scenario is implied: use this when a user has source code or invention text and wants a single patentability score. However, it does not explicitly say when to use this instead of precheck_pillars, precheck_prior_art, or precheck_compare_to_patent, nor does it list exclusions or conditions.

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

All Patent PreCheck toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources