Get a graph neighbourhood

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

Annotations already declare the operation read-only, idempotent, and non-destructive; the description goes beyond these by explaining that the response includes edges and predicates, not just nodes. It also warns about the cost of deeper traversal ('depth 3 gets large quickly and is capped') and points to get_vocabulary for predicate semantics, which is useful operational context.

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?

Three concise sentences, each carrying useful information: the main function, the filtering techniques, and the expectations about depth. No filler or redundant wording; the formatting with occasional capitals is minor.

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?

Without being verbose, the description covers all critical context an agent needs to make a correct invocation: what is returned, how to filter, how depth affects cost, and where to look up predicate meanings. The output schema and comprehensiveness annotation cover the remaining details, so nothing essential is missing.

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?

Since the schema has 100% parameter description coverage, the baseline is 3, but the description adds meaningful semantic depth: type is used to 'ask a shaped question,' predicate narrows the graph to one kind of edge, and depth is contextualized as ranging from direct links to a fast-fan-out cap. These are real interpretation gains beyond the schema's literal field descriptions.

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 explicitly defines the tool as returning everything within N hops of a document along with the connecting edges and their predicates. It clearly states the resource (graph neighborhood) and the action (get/traverse), making the tool’s behavior distinct from simple document fetches or direct-connection lookups.

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 gives practical context for when to use the tool: asking what a passage, person, or theme is connected to without fetching each document. It explains how filtering by type and predicate can shape the query and warns about frontier growth, but it does not explicitly name or contrast siblings like get_connections or get_family, so the guidance is not exhaustive.

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