neighbourhood

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, but the description adds valuable behavioral context: seven relations are recorded facts while 'similar' is inferred from a cosine score. It also warns the agent about the 'Related' relation, which is not generic but task-judgment sensitive. This materially shapes invocation and result interpretation.

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 but information-dense: it front-loads the action, then packs the eight relation names and the key fact-vs-inference distinction into a few terse sentences. Every sentence contributes behavioral or selection value, with no filler.

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 output is a graph of neighbours with relation types, and no output schema is provided; the description still tells the agent what to expect (relations and their provenance) and how to use it. Gaps are minor: it doesn't fully define what a 'neighbour' edge looks like, but coverage is sufficient for correct invocation.

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 about 100%: kbid is 'The section to look around' and the limit is 'Maximum neighbours to report (default 20)'. The tool description adds no additional parameter meaning beyond the schema, so the baseline of 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 starts with a specific verb-resource pair: 'List what relates to a section and HOW'. It enumerates the eight relation types and explains which are recorded facts versus inferred, clearly distinguishing this navigation tool from content/search/recall 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 gives a clear usage context ('so you can decide what to read next') and explicitly warns that 'Related is not relevant -- judge these against your task.' It could be stronger by contrasting it to specific sibling tools like search or retrieve, but the intended selection condition is clear.

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