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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral detail the annotations cannot convey: traversal is bidirectional (outgoing links and incoming references) and each neighbour carries a relationship type. It omits edge cases such as isolated units or result limits, so not a 5.

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, zero filler, and the core semantics (what neighbours means, both directions) are front-loaded before the usage hint. Every clause earns its place.

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?

An output schema exists, so return-value detail is not required, and the description still summarizes the shape (neighbours with relationship types). It is essentially complete for a 3-parameter read tool; only minor edge-case behavior (empty results, traversal depth) is unaddressed.

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 100% and all three parameters (slug, domain, locale) are fully documented in the schema, including enum values and the handbook/HRN special case. The description only says 'given a unit' and adds no parameter meaning beyond that, so the baseline 3 applies.

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 gives a specific verb (traverse/return neighbours) on a specific resource (the knowledge graph), and defines the output precisely as outgoing links plus incoming references with relationship types. It is clearly distinguishable from the get_* siblings, which fetch a single unit rather than its graph neighbourhood.

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 explicitly states when to reach for it: 'Use this after a `get_*` call to widen an answer with adjacent units.' That is a clear usage context tied to a named sibling family. There is no explicit when-not or boundary case (e.g. no-neighbour units), so it stops short of a 5.

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