traverse

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

With no annotations provided, the description fully bears the responsibility for behavioral disclosure. It explicitly states that archived records are included, that truncated flags indicate limits were hit, and that reads do not authorize writes. These are important behavioral traits beyond what the schema or output schema would convey. No contradictions exist.

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 dense and information-rich, with no wasted words. It front-loads the core purpose and example before diving into parameter details. Each sentence adds value, covering return values, limits, filtering, archived records, and permission caveats. It is slightly long but appropriate for the tool's complexity.

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 complexity (6 parameters, output schema present), the description covers the essential aspects: what it returns (preview, depth, shortest path, relationships), limits, filtering, archived records, and the permission caveat. The existence of an output schema covers return structure details. The only notable gap is the lack of explanation for the direction parameter, which is a meaningful omission for a traversal tool. Overall, it is nearly complete but falls short of exhaustive.

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 0%, so the description must compensate. It explains relationship_types (restricts which link types are followed), collection_id (filters returned records without blocking routes), and max_nodes (caps reached records with truncation flags). It also clarifies max_depth as 1–4 hops. However, it omits any explanation of the direction parameter (outgoing/incoming/both), which is non-obvious and would benefit from a brief clarification. Start_record_id is self-evident.

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 walks explicit links breadth-first up to a depth, with a concrete example chain (person -> applications -> openings/interviews -> feedback). It specifies the resource (links) and the operation (walk), and the unique focus on graph traversal distinguishes it from siblings like search_records or batch_read. The purpose is unambiguous and well-scoped.

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 clear context for when to use the tool (traversing relationships) and includes a caution that reading does not authorize writes, guiding the agent to resolve before mutating. However, it does not explicitly name alternatives or state when not to use it, such as when a simple batch read would suffice. It lacks explicit exclusions but the context is sufficiently clear.

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