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

Annotations already mark it read-only and non-destructive; the description adds substantial behavioral disclosure: determinism, 5,000-row cap, caller-supplied data, no retention, and input modality restrictions. These are meaningful operational traits an agent needs and are not present in the annotations.

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 compact and information-dense after the initial title-like sentence. It front-loads capabilities and then adds constraints; the mild redundancy between title and first sentence prevents 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 description covers purpose, input nature, limits, determinism, privacy, and scope, which is strong for a complex tool. Because an output schema exists, the absence of return-value details is acceptable; the only notable gap is body schema internals, already reflected in parameter semantics.

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 schema only exposes a generic 'body' object, so useful meaning must come from the description. The description explains the high-level payload intent (numeric vectors and modes) but does not specify required fields, formats, or mode-selection keys, leaving a gap for invocation.

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 specific operations ('cluster subjects, discover roles from behaviour + relationship edges, detect emergent roles, or match against exemplars') on a defined resource (caller-supplied numeric vectors). The title and description align, and the deterministic, non-biometric framing separates it from the read-only get_* siblings.

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 clearly conveys when to use this tool: when behavioral segmentation, role discovery, or exemplar matching is needed over caller-supplied numeric vectors. It adds exclusions (no audio/video/affect inference, no retained data) and constraints that define suitability, though it does not explicitly name alternative tools or contrast them.

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