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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds real behavioral context beyond them: the 2-hop relationship.path cap, the fact that root models additionally return peer audiences composable via the audience predicate, and the distinction between path (warehouse column) and legacy label. It stops short of describing result shape or size limits when a model has many neighbors.

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 core capability and the iterative call pattern are front-loaded, followed by attribute semantics and the hop-cap constraint. Every sentence carries information, though the displayName/description/piiMask sentence is dense and could be tightened.

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 no output schema, the description does the work of explaining what comes back: attributes, neighbor attributes, relationship metadata, peer audiences for roots, and optional metadata fields. Remaining gaps are minor for a two-parameter read tool — notably the meaning of workspace_id and any guidance on large neighbor sets.

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 50%: model_id is documented in the schema, workspace_id is not. The description meaningfully extends model_id by tying it to the iterative 2-hop walk and clarifying it accepts any model, root or not, but it says nothing about workspace_id, leaving half the parameters unilluminated.

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 names a specific verb and resource: returns model attributes plus 1-hop reachable neighbors with relationship metadata, for any model in the data graph, root or not. That scope statement distinguishes it from list_audience_subjects and get_audience, though it never names a sibling explicitly.

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?

It gives a concrete procedure: call first with the chosen subject, then iterate using a 1-hop neighbor's modelId to reach 2 hops, and it notes the backend caps relationship.path at 2 hops. It does not state when to prefer this over list_audience_subjects or how it relates to preview_audience, so alternatives are implied rather than spelled out.

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