WritersLogic verifiable AI agents

prior-art-invalidator

Global Prior-Art Patent Invalidator — Screens a patent's claims against scholarly literature published before the priority date (arXiv, OpenAlex, Europe PMC, Crossref, HAL, J-STAGE; English, Chinese, Japanese, German; not patent databases). Give claims plus a priority date, or a patent number to read them from Google Patents. Claims are split into elements in code; every claim-chart quote is verified verbatim against the title or abst

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "prior-art-invalidator"
  }
}

Input Schema

Name	Required	Description
`patentNumber`	No	Publication number such as US7629993B2. Claims, priority date and cited art are read from Google Patents when the claims or the date are omitted, and the date is cross-checked otherwise. Required unless both patentClaimsText and priorityDate are given.
`priorityDate`	No	Earliest effective filing/priority date, YYYY-MM-DD. Only works published strictly before it count. Optional when patentNumber is given; a supplied date wins over the Google Patents date and a disagreement is reported.
`patentClaimsText`	No	Claims to attack, numbered as in the patent (e.g. "1. A method ..."). Optional when patentNumber is given: the independent claims are then read from Google Patents. A dependent claim is charted with every element of its parents.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full disclosure burden, and it does meaningful work: it states that claims are split into elements in code and that every claim-chart quote is verified verbatim against the title or abstract, which tells the agent the output is grounded rather than generated. It also discloses the source corpus and language coverage. It does not address cost, latency, or what a partial/negative result looks like, and the final sentence is cut off mid-word.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the opening clause, which is good. However, the dense parenthetical catalogues of databases and languages compete for attention, and the description terminates mid-word ('the title or abst'), leaving a key behavioral claim incomplete. The truncation is a real structural defect, not just a stylistic quibble.

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 three-parameter tool with no output schema and no annotations, the definition covers inputs, data sources, language scope, an explicit exclusion, and the verification discipline behind the claim chart. What is missing is any picture of the return value — the shape of a claim chart, what a 'no prior art found' result looks like — which matters more here precisely because no output schema exists.

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 description coverage is 100%, so every parameter is already documented in structured form, including the patentNumber/claims/date interaction and the rule that a supplied date overrides the Google Patents date. The description restates that same either/or relationship without adding format details, such as how claims should be numbered or how much claim text is practical. Baseline 3 is appropriate when the schema does the heavy lifting.

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 specific verb and resource ('Screens a patent's claims against scholarly literature published before the priority date') and scopes it precisely with source databases, supported languages, and an explicit exclusion ('not patent databases'). That exclusion alone separates it from siblings like precedent-search and patent-design-around without needing to open 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 invocation rule: 'Give claims plus a priority date, or a patent number to read them from Google Patents,' which tells the agent the two valid input modes. The 'not patent databases' note rules out a plausible but wrong expectation. It stops short of naming when a sibling tool would be the better choice, so it is strong context rather than full routing guidance.

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

All WritersLogic verifiable AI agents tools Inspect

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

Need Help?