Traverse the Knowledge Graph

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds meaningful behavioral context by explaining that it returns one-hop neighbours in both directions and includes relationship types, which is not stated in the annotations or schema.

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?

Two sentences accomplish a lot: they state the operation, the input, the output shape with directions, and the recommended invocation context. There is no wasted wording, and the key behavior is front-loaded.

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?

With an output schema present, annotations covering safety, and the description explaining usage and return semantics, the definition is largely complete. It does not mention pagination, recursion depth, or how locale affects the results, but these are not critical given the existing schema and read-only nature.

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 coverage is 67%, and the description does not add much parameter-specific detail beyond what the schema provides. It clarifies the conceptual role of slug/domain as a 'unit' and mentions locale defaults elsewhere, but it does not describe domain enum meanings or the exact expected relationship between parameters.

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 states a specific operation—traversing the knowledge graph from a given unit to its neighbours—and specifies what is returned: outgoing and incoming units, each with a relationship type. This clearly distinguishes it from sibling get_* and list_* tools that fetch single units or enumerate lists.

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 gives clear when-to-use guidance: use it after a `get_*` call to widen an answer with adjacent units. It does not explicitly say when not to use it or name alternatives, but the contextual instruction is sufficient for typical agent selection.

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