search_patents

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose real mechanics beyond the schema: a size ceiling of 1000, keyset pagination via 'after' taken from the prior page's last sort values, and the 'lapse' opt-in for the expiry field group. It omits permission/auth requirements, whether the corpus is only granted patents (no pending applications), and any result-count or rate limits.

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?

Purpose is front-loaded and every clause adds information, with concrete inline examples rather than prose. The telegraphic style ('f the fields to return', 's the sort') compresses well but reads as fragmented, which slightly slows parsing of an already dense grammar.

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?

For a complex JSON-DSL query tool with 0% schema coverage, the description supplies worked examples for the query and sort, the field-projection option, the page-size ceiling, and the cursor chaining rule. An output schema exists, so return values need not be described, and the remaining detail is delegated to a named, versioned grammar ('PatentSearch v1').

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 0% and the params are nested free-form objects, yet the description explains each of the five: q as single-key JSON with worked examples, f as a field projection with the 'lapse' group enumerated, s as sort with an example, size with its cap, and after as the cursor. The gaps are the default size of 25 and any enumeration of the permitted grammar operators beyond _and/_gte.

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?

States a specific verb and resource ('Search granted US patents') and pins the scope to granted US patents, which implicitly separates it from search_disclosures and similar_patents. It does not name any sibling explicitly, so an agent must infer the boundary from the scope wording alone.

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?

Usage is only implied: the description tells you how to query, not when this tool is the right choice over search_disclosures, similar_patents, or check_patent_status. There are no exclusions, prerequisites, or routing rules, so selection among the 14 siblings is left to inference.

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