usptoppubs_search

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

No annotations exist, so the description carries the full burden, and it delivers: it discloses the authoritative data source, the corpus scope (granted patents and published applications), the normalization behavior of bibliographic output, the public nature of the data, and the advanced query syntax capabilities. It does not explicitly discuss pagination limits or error behavior, but the described behavior goes well beyond what the input schema provides.

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?

Every sentence earns its place: the first establishes scope, the second the output shape, the third the crucial query-parameter semantics with examples, and the fourth adds provenance. The core action is front-loaded, and the density is appropriate for a tool with a complex query syntax.

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?

This four-parameter search tool has no output schema and no annotations, and the description compensates exceptionally well by enumerating returned fields, scoping the corpus, and detailing query capabilities. The only gaps are that the full field-code table is delegated externally and the relationship to usptoppubs_detail (when to fetch single-patent details) is left implicit. Doesn't explain the output schema boundaries, but also doesn't need to.

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 input schema already describes all four parameters (100% coverage), so the baseline is 3. The description adds meaningful value beyond the schema by giving concrete query syntax examples (battery.ti., Microsoft.as, date-range patterns) and directing the agent to the markdown doc for the full field-code table, which materially improves the chance of constructing a valid query.

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?

Description states a specific verb and resource: searches USPTO Patent Public Search full-text index for granted patents and published applications, returning normalized bibliographic results with a concrete field list. The phrase USPTO's own distinguishes it from the googlepatents_* siblings, and the emphasis on bibliographic results separates it from usptoppubs_detail. No ambiguity about what the tool does.

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?

Clear context is provided: this is for querying USPTO's official full-text patent index, with the qualifier USPTO's own contrasting with Google-based patent search alternatives. However, it does not explicitly name alternatives like googlepatents_search or state when not to use this tool versus usptoppubs_detail.

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