patent_search

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

Annotations already include readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, but the description adds valuable context: company name variations are matched automatically, results include bibliographic details, zero-result/error responses come as structured JSON with recovery hints, and results stay fresh for 24 hours. This goes beyond annotation fields and sets clear expectations for behavior.

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 front-loaded with the core purpose and use cases, then provides query types, result details, alternative tools, and freshness. Every sentence contributes value; however, it is slightly longer than necessary, with some details (e.g., 'structured JSON with recovery hints') that could be inferred from output schema. Still, no fluff and well-organized.

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 the tool's complexity (11 params, 0 required) and that an output schema exists, the description is thorough: it explains what queries work, what results contain, how errors are returned, and how freshness is handled. It also addresses sibling differentiation and gives practical examples. No missing critical context for an agent to select and invoke correctly.

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 description coverage is 100%, so the baseline is 3. The description adds semantic context beyond the schema by providing example patent number format, explaining that assignee name variations are auto-generated, and explicitly linking query types to the search_type enum (prior art, landscape, specific). This adds meaningful interpretation without duplicating the schema.

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 states the verb 'Search' and resource 'patents' with specific use cases (prior art, landscape mapping, specific lookup). It clearly distinguishes from siblings by naming academic_search and web_search as alternatives, and outlines query types (patent number, description, company, inventor). This exceeds the minimum viable clarity.

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?

Provides explicit usage guidance: 'Reach for this when the question is about inventions or IP' and names alternatives ('use academic_search for research papers or web_search for general technical content'). Also mentions automatic company name matching and structured error responses, giving clear context for when to use this tool over siblings.

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