Patent Search

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

With no annotations provided, the description should disclose key behaviors. It claims 'Get all patents' but the schema shows a limit parameter (default 20, max 50), meaning it does not return all patents in most cases. This is a significant behavioral inconsistency not addressed. Also, no information on pagination, rate limits, or read-only nature.

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 sentence, very concise and front-loaded. However, the phrase 'Get all patents' is potentially misleading given the limit parameter, slightly reducing effectiveness.

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?

The tool has no output schema and the description does not explain the return format (e.g., patent IDs, full details). While adequate for a list tool, it lacks completeness regarding what the agent will receive.

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?

The schema has 100% parameter description coverage, so the baseline is 3. The description adds value by stating the results are 'sorted by most recent', which is not in the schema. However, it could clarify the limit parameter's effect on 'all'.

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 clearly states the verb 'Get', the resource 'patents assigned to a specific company', and the sorting order 'sorted by most recent'. It effectively distinguishes from siblings like get_patent_detail (specific patent) and search_patents (broad search).

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 context (when you need patents for a specific company) but does not explicitly state when not to use it or provide alternative tools for different scenarios. No exclusions or comparisons are given.

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

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

No annotations provided, so description carries full burden. It states the tool retrieves details, but does not disclose behavioral traits such as read-only nature, authentication requirements, rate limits, or any side effects. Minimal transparency beyond the obvious.

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?

Single sentence that front-loads the purpose and lists key contents. No redundant words. Perfectly concise.

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?

No output schema, so description explains return data includes abstract, claims, inventors, citation data. This is sufficient for a simple retrieval tool. Missing details on error handling or format, but overall adequate.

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% (one parameter fully described with example). Description does not add semantic meaning beyond the schema; it merely repeats that patent_id is a USPTO number. Baseline 3 for high coverage.

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?

Clearly states the verb 'Get' and the resource 'full details for a specific patent'. Lists included data (abstract, claims, inventors, citation data). Distinguishes from sibling tools by specifying 'specific patent', contrasting with get_company_patents (company-specific) and search_patents (searching).

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?

Implies usage when needing full details for a known patent, but provides no explicit guidance on when not to use (e.g., if only basic info needed) or alternatives. No exclusion criteria mentioned.

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

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

No annotations are provided, so the description carries the full burden. It mentions using the PatentsView API and a max result limit of 25, but does not disclose rate limits, pagination, or behavior on no results. Basic but not rich.

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?

A single, front-loaded sentence that conveys the core function. No wasted words.

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 no output schema, the description does not explain return values, which would be helpful. However, for a simple search tool with 4 well-documented parameters, it is minimally adequate. Could mention typical response fields.

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%, with each parameter described. The tool description reiterates the parameter types (keyword, assignee, inventor) but adds no extra semantic value beyond the schema. Baseline 3 is appropriate.

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 clearly states the tool searches USPTO patents by keyword, phrase, assignee, or inventor name. It specifies the API source (PatentsView) and distinguishes from siblings like get_company_patents (company-specific) and get_patent_detail (detail retrieval).

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 by listing search criteria, but it does not explicitly state when to use this tool versus its siblings. For example, it could mention that get_company_patents should be used for company-focused searches, or get_patent_detail for specific patent info.

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