links

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

With zero annotations the description carries the full burden and largely meets it: it discloses the traversal depth cap ("up to 3 hops"), the return payload (source section, anchor, broken flag, outside-store flag), and implies a pure read operation. It still does not state ordering, volume/pagination behavior for high-degree notes, or cost of a 3-hop traversal – things an agent planning a call would want.

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 dense sentences, front-loaded with the resource followed by the direction vocabulary and then the return shape; every clause adds information. Minor deduction: the mid-sentence line break and the slightly telegraphic style make it read as a fragment rather than a self-contained statement.

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?

No output schema and no schema descriptions, so the description is the only documentation and it covers direction semantics, traversal limit, and return fields adequately. The remaining gap is the required "path" parameter's format, which is the one thing an agent could plausibly get wrong on the first call.

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 0%, so the description must compensate, and it does for the two non-obvious parameters: direction is given a value vocabulary (out/in/both) that the schema lacks an enum for, and depth is bounded (max 3 hops). It adds nothing about "path" itself – no indication of accepted format (vault-relative path vs. note identifier) or the relationship between default depth 1 and the 3-hop cap.

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?

"Links of a note" names the resource and the retrieval verb implicitly, and the out/in/both gloss makes the exact scope unambiguous. It is not confused with any sibling (read, search, source), though it stops short of an explicit verb like "list" or "retrieve".

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 implicitly tells you when this is the right tool (you want the link graph of a specific note, in one or both directions), and the out/in/both breakdown helps pick a direction. There is no explicit when-not-to-use guidance, no mention of sibling alternatives such as search or source, and no note on whether this works for non-existent or external paths.

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