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

With no annotations, the description carries the full burden and does substantial work: it discloses the response style ('same response style as ask'), how neighbors are clustered, and what each mode returns. It does not explicitly state that the operation is read-only or that it has no side effects, which is the main residual gap.

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?

Front-loads the core purpose with 'PRIMARY', then spends each following clause on a distinct mode — no filler. It is a single dense paragraph rather than a scannable list, which costs it a point on structure but not on economy.

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?

There is no output schema, and the description compensates by explaining how results are grouped and which sibling's response style to expect. Combined with the mode semantics, an agent has enough to invoke it correctly; only the read/write safety profile is unstated.

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 100%, so the baseline is 3, but the description goes beyond the schema by giving the meaning of each enum value for `direction` — the schema itself only lists the six literals without explaining them. That is genuine added semantic value for the one parameter an agent must reason about.

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?

States a concrete verb and resource — 'explore the neighborhood of a piece' — and immediately qualifies the output ('neighbors grouped into argument shapes'). It is clearly a graph-exploration tool distinct from retrieval siblings, though it never names a sibling to contrast against.

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?

Each direction value is given a usage semantics ('tensions filters to high-contrast edges', 'peripheral returns pieces sensed-not-connected'), and pivot gets an explicit when-to-use scenario. There is no explicit 'when not to use this vs. get_connections/navigate/traverse' guidance, so it stops short of 5.

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