object_traverse

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 only mentions 'bounded depth' and 'cataloged relation', failing to state read-only nature, pagination via cursor, filtering behavior, max_nodes limits, or error cases. This is a significant gap for an operation that likely traverses a complex graph.

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, front-loaded sentence with zero wasted words. However, given the tool's complex nested schema, such extreme brevity borders on under-specification rather than being appropriately sized, so it doesn't earn 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?

The tool has a highly complex input schema with nested filter structures, no annotations, and an output schema (per context). The description covers only the basic traversal concept, omitting filtering, pagination, max_nodes constraints, and context_id semantics. The output schema mitigates return-value description needs, but the input side is still critically incomplete.

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%, and the description compensates only for 'roots' (ObjectRef roots) and 'depth' (bounded depth). It ignores critical parameters like filters, cursor, max_nodes, wave_id, and relation, leaving the agent to infer their meaning from the raw schema. The complex Where* filter types are entirely unexplained.

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 operation ('Traverse') and the resource ('cataloged relation') with specific modifiers ('ObjectRef roots', 'bounded depth'). This distinguishes it from object_get and object_query by focusing on relation traversal. However, it doesn't explicitly differentiate from the sibling tool 'trace', so it stops short of a 5.

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 guidance is given on when to use this tool versus alternatives like object_query or trace. The description does not mention any exclusions, prerequisites, or contextual conditions; the only hint is the verb 'Traverse', which merely implies a use case rather than stating it.

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