hidim

Overview Schema Source Related Servers Discussions Admin

loadings

Extract PCA component feature weights to find the strongest positive and negative features, or return all weights in feature order to inspect level, slope, and curvature patterns.

Instructions

Loading vector of one principal component of a PCA embedding made by project(method='pca'): the strongest positive and negative features, or the whole vector in feature order (all_features=True) to read shapes such as level/slope/curvature.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "loadings"
  }
}

Input Schema

Name	Required	Description	Default
`top`	No
`name`	Yes
`component`	No
`all_features`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Nov 9, 2026

TDQS

A3.8/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses the two return modes — default gives the strongest positive and negative features, all_features=True gives the full vector in feature order — but says nothing about failure behavior when the embedding is not PCA, sign conventions, or cost of requesting all features.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the resource stated first and the mode flag parenthesized inline. Nothing is redundant, though the trailing clause about level/slope/curvature is somewhat compressed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. However, with zero schema coverage and no annotations, the definition should say more about what 'name' identifies and how 'top' interacts with 'all_features'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It gives meaning to 'top' (strongest positive and negative features), 'component' (which principal component), and 'all_features' (whole vector in feature order), but leaves 'name' completely unexplained and does not clarify whether 'top' means N per sign or N total.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: the loading vector of one principal component from a PCA embedding. It also pins down the producing sibling ('made by project(method='pca')'), so an agent can tell this apart from project, describe, or plot without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The prerequisite is implicit but clear: it only applies to embeddings produced by project(method='pca'), and it names a concrete use case (reading level/slope/curvature shapes). It stops short of explicit when-not guidance or naming an alternative tool for non-PCA embeddings.

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