Retrieve a note's typed neighbors by bucket to distinguish governing constraints, grounding evidence, execution context, and weaker see-also links.
Typed neighbours of a note. The eight buckets are not equivalent: Governed by and Read first are constraints, Source and Evidence are grounding, Applied in is where it is executed, See also is the weakest.
| Name | Required | Description | Default |
|---|---|---|---|
| note | Yes | ||
| buckets | No | comma-separated subset |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden. It does disclose genuinely useful semantics — that the eight buckets have unequal strength and what each family means — but omits default behavior when 'buckets' is omitted, error handling for unknown notes, and any read-only assurance.
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 sentences, front-loaded with what the tool returns, then the payoff sentence on bucket hierarchy. Dense but not padded; the only weakness is the clipped noun-phrase opening.
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?
For a two-parameter read tool with no annotations and no output schema, the description covers the conceptual output structure well but leaves the default bucket set, per-neighbour return shape, and note identifier expectations unspecified.
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 only 50% and there are no enums, so the description must compensate. It names six of the eight valid bucket values (Governed by, Read first, Source, Evidence, Applied in, See also) and explains their relationships, which the schema's bare 'comma-separated subset' does not; it stops short of listing all eight or the exact token format.
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 names the resource ('neighbours of a note') and the qualifier 'typed', so an agent can tell it returns graph-related notes rather than note content (vault_get) or a search result set. It lacks a verb and makes no explicit sibling contrast, but the scope is unambiguous.
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?
There is no statement of when to call this versus vault_get, vault_impact, or vault_gaps. The bucket commentary describes how to interpret output, not when the tool is the right choice, so usage is only faintly implied by the resource name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.