NEXO Brain

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 states the tool lists and groups learnings, which implies a read-only operation, but doesn't explicitly confirm it's non-destructive or safe. It also doesn't mention potential behaviors like pagination, rate limits, authentication requirements, or what happens when no learnings exist. For a tool with zero annotation coverage, this leaves significant gaps in understanding its operational characteristics.

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 concise and well-structured: the first sentence states the core purpose, and the 'Args' section clearly explains the parameter. There's no wasted text or redundancy. However, it could be slightly more front-loaded by integrating the parameter explanation into the main description, but the current two-part structure is still efficient and easy to parse.

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 (one optional parameter) and the presence of an output schema (which handles return values), the description is reasonably complete. It covers the purpose, grouping behavior, and parameter usage. The main gap is the lack of behavioral details (e.g., safety, performance), but with an output schema and simple inputs, this is less critical. For a list tool with minimal parameters, it provides sufficient context for basic use.

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 description adds meaningful semantics for the single parameter: it explains that 'category' is optional, used for filtering, and that an empty value shows all grouped learnings. Since schema description coverage is 0% (the schema only defines the parameter type and default without description), the description fully compensates by clarifying the parameter's purpose and behavior. With 0 parameters documented in the schema, the baseline is 4, and the description meets this by providing clear, actionable information.

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 clearly states the tool's purpose: 'List all learnings, grouped by category.' This specifies the verb ('List'), resource ('learnings'), and grouping behavior. It distinguishes from siblings like 'nexo_learning_search' (which likely searches rather than lists) and 'nexo_learning_add/delete/update' (which are mutations). However, it doesn't explicitly differentiate from 'nexo_learning_search' in terms of filtering vs. listing, which prevents a perfect score.

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 provides implied usage guidance: it mentions an optional 'category' parameter for filtering, suggesting this tool is for retrieving learnings with optional category-based filtering. However, it lacks explicit guidance on when to use this versus alternatives like 'nexo_learning_search' (which might support more complex queries) or 'nexo_entity_list' (which might list entities instead of learnings). No exclusions or prerequisites are stated.

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