NEXO Brain

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

No annotations are provided, so the description carries full burden. It states it 'lists' preferences, implying a read-only operation, but doesn't disclose behavioral traits like whether it requires authentication, returns paginated results, has rate limits, or what happens if no preferences exist. The grouping aspect is mentioned but not elaborated (e.g., how categories are determined).

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, efficient sentence: 'List all preferences grouped by category.' It's front-loaded with the core action and resource, with no wasted words. Every part of the sentence contributes meaning (listing, scope 'all', resource 'preferences', grouping method).

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 low complexity (single optional parameter) and the presence of an output schema (which handles return values), the description is reasonably complete for a listing operation. It covers the purpose and grouping aspect. However, it lacks details on authentication, error handling, or behavioral constraints, which are important even with an output schema.

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 has one parameter ('category') with 0% description coverage (no schema descriptions). The tool description doesn't add any parameter-specific information—it doesn't explain what the 'category' parameter does (e.g., filters results to a specific category, defaults to all categories). Since schema coverage is low, the description fails to compensate, but the parameter count is minimal (1), keeping it at baseline.

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 'List all preferences grouped by category' clearly states the verb ('List') and resource ('preferences'), and specifies the grouping method ('by category'). It distinguishes from siblings like nexo_preference_get (retrieves a single preference) and nexo_preference_set (sets a preference). However, it doesn't explicitly mention what 'preferences' refer to in this context (e.g., user settings, system configurations).

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?

No explicit guidance on when to use this tool versus alternatives. The description implies it's for listing preferences, but doesn't specify scenarios (e.g., 'use to review all user settings' or 'use instead of nexo_preference_get for bulk retrieval'). It mentions grouping by category but doesn't explain when this is beneficial or if there are alternatives for ungrouped lists.

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