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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: the graph is derived purely from authored [[name]]/`.md` links rather than embeddings, and ambiguous names return a disambiguation list instead of failing.

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-loaded with the payoff (what the graph view contains), then the underlying data source, then input handling. Three sentences all carry information, though the link-syntax parenthetical adds mild detail an agent may not need to call the tool.

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?

With no output schema, the description carries the burden of describing return content and does so enumeratively: links out, links in, one-hop neighbours, and broken links, plus the disambiguation list. For a one-parameter read tool this is sufficient to call correctly.

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% with an example value, so the baseline is 3; the description earns above that by explaining the accepted forms (path or name) and, importantly, the conditional result when a name is shared by several documents.

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?

Names a specific resource and relationship set: outbound links, backlinks, one-hop neighbours, and broken links for a given document. The clause "Built from the links you write... no embeddings" separates it cleanly from search/recall siblings that work on semantic similarity.

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?

Gives clear context for when this is the right tool (you want link structure, not content search) via the explicit "no embeddings" contrast, and tells the caller what input form to supply. It stops short of naming an alternative sibling or stating exclusions, so it is context-setting rather than full routing guidance.

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