googlepatents_suggest

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It addresses this well by stating the data is 'Public data' and 'sourced from Google Patents' own search API,' signaling that no authentication is needed and clarifying the provenance. It also says output mirrors the suggestions shown on the real UI, which sets expectations about what the response represents, but it does not cover details like response shape, error behavior, or rate limits, which are common for autocomplete endpoints.

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 appropriately brief at three sentences, with the core intent front-loaded: 'Autocomplete an inventor or assignee name for Google Patents search.' The second sentence adds useful context about the matching advanced-search-page behavior, though it repeats 'autocomplete' and 'inventor or assignee name' from the first sentence. The data-source sentence is compact and earns its place, but the redundancy keeps it from a 5.

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 is a straightforward tool with two fully documented parameters, no annotations, and no output schema. The description adequately covers when to use it, where the datacomes from, and that it is public data. It somewhat addresses the unspecified output by stating the helper 'Returns Google Patents' own autocomplete suggestions,' which tells an agent that the likely output is a list of names, but does not specify the precise return structure. Given the simplicity of the tool, this is adequate and warrants a 4.

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% with both 'field' and 'value' descriptively documented, so the baseline score is 3. The description reinforces the parameter purpose ('inventor or assignee' for field, 'as the user types' for value) but adds no material insights beyond the schema, such as how partial name matching works, case sensitivity, or whether the field supports other values. Thus, the description does not meaningfully expand parameter meaning.

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 opens with a specific verb and resource: 'Autocomplete an inventor or assignee name for Google Patents search.' It clearly distinguishes this from the sibling googlepatents_search (full-text patent search) and googlepatents_detail by focusing solely on the autocomplete behavior for the Inventor/Assignee fields. The mention of matching the advanced search page's suggestions further reinforces its unique role.

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 clearly implies the appropriate use case: retrieving autocomplete suggestions as the user types a partial inventor or assignee name. It specifies that these suggestions align with the Inventor/Assignee fields on Google Patents' advanced search page, giving the agent context about the intended purpose. However, it doesn't explicitly name alternative tools (e.g., googlepatents_search) or state when NOT to use this tool, so it falls just shy of a 5.

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