Screen ONE US patent by publication number (e.g. USD689332S1): compute its statutory expiry/status, join CPSC recall-safety for its category, and run an OFAC/OIG screen on the assignee. Returns the freedom-to-operate read (design-patent scope; not legal advice).
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional category label to sharpen the recall match. | |
| publication_number | Yes | US patent publication number, e.g. USD689332S1 or US8935905B2. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full behavioral burden. It discloses three operations and the outcome (freedom-to-operate read) plus a disclaimer. Missing details on whether the tool is read-only or has side effects, but overall transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single efficient sentence covering purpose, inputs, actions, and output. Slightly dense but clear; could be broken into two sentences for readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given complexity (three checks) and no output schema, description explains return value (freedom-to-operate read) and includes a disclaimer. Does not describe output format or structure, which might be needed for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context by providing an example (USD689332S1) and noting category sharpens recall match, but it largely mirrors schema text. No additional meaning beyond that.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool screens one US patent by publication number and lists three specific computational actions (expiry/status, CPSC recall-safety, OFAC/OIG screen). It clearly distinguishes from siblings by focusing on a single patent rather than categories or lists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for individual patent screening but lacks explicit when-not-to-use or alternative tool references. Sibling names provide differentiation, but no direct guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: listing categories, providing a cross-category feed, generating a paid report for a category, and screening a single patent. No overlap in functionality.
Tool names use a mix of patterns: verb_noun (list_categories, screen_patent), noun_noun (category_opportunity_report), and adjective (newly_expirable). While each name is descriptive, the lack of a consistent convention reduces predictability.
With 4 tools, the server is well-scoped for its niche domain of design patent expiration tracking. Each tool serves a necessary function without redundancy or bloat.
The tool set covers the core workflow: listing categories, viewing expiring patents, generating a detailed report, and screening individual patents. Missing a direct tool to list all patents in a category without the paid report, but the critical paths are supported.