Detect emergent clusters and hierarchy in a vector collection. Returns JSON cluster members, centroids, and sizes, filtered by a minimum cluster size.
Detect emergent structure/hierarchy in collection. Returns a JSON array of clusters, each {cluster_id, members: [...], centroid, size}, filtered by min_cluster_size.
| Name | Required | Description | Default |
|---|---|---|---|
| collection | Yes | ||
| min_cluster_size | No |
Changes observed during successful MCP inspections.
v4.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose the return shape (cluster_id, members, centroid, size) and that results are filtered by min_cluster_size, but it never states whether the call is a read-only computation, how expensive it is on large collections, or whether clustering is deterministic across runs.
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 compact sentences: purpose first, return contract second. No filler, and the output shape is stated in one clause rather than a paragraph.
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?
Because there is no output schema, the inline return contract is genuinely necessary and present. However, with zero annotation coverage and an undocumented schema, the definition still leaves an agent guessing about the semantics of `collection`, compute cost, and whether the operation mutates state.
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 0%, so the description must compensate. It names both parameters in context and clarifies that min_cluster_size acts as a filter on returned clusters, but it never says whether `collection` is a name, ID, or handle, nor the units/effect of the threshold (minimum members per returned cluster).
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?
States a specific verb and resource: 'Detect emergent structure/hierarchy in `collection`'. An agent can tell it is an analysis/partitioning operation, but nothing distinguishes it from sibling analyzers like hyperspace_analyze_geometry or hyperspace_get_subsumption_tree.
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?
Usage is only implied by the word 'clusters'. There is no explicit when-to-use, no mention of when a sibling (e.g. get_subsumption_tree, analyze_geometry) would be the better pick, and no prerequisites such as needing indexed points in the collection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.