Skip to main content
Glama

Winsorize extreme observations

bpj_series_winsorize
Read-onlyIdempotent

Clamp tail observations to the retained order-statistic boundaries in input order.

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": {
      "values": "<values>",
      "fraction": "<fraction>"
    },
    "name": "bpj_series_winsorize"
  }
}

Input Schema

NameRequiredDescriptionDefault
valuesYes
fractionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description does add real value by stating that observations are clamped (not dropped) to retained order-statistic boundaries and that ordering is preserved, which clarifies that output length equals input length. It still omits edge-case behavior such as ties, non-finite values, or what happens at fraction=0.

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 front-loaded sentence with no filler, and the ordering guarantee is placed at the end where it belongs. It is arguably under-sized for a tool with zero schema coverage, but nothing is wasteful or buried.

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?

For a two-parameter, annotation-covered, no-output-schema read transform, the description delivers the core semantics. It falls short on the JSON-string encoding of 'values', per-tail fraction semantics, and the fact that output is a same-length list of clamped values, all of which an agent needs to call it correctly the first time.

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

Parameters2/5

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

Schema description coverage is 0%, and the description says nothing about either parameter. Critically, 'values' is typed as a string with title 'Number array (JSON)', and nothing in the description warns that the array must be JSON-encoded rather than passed as a native array, nor that 'fraction' applies independently to each tail (bounded at 0.49). Both are easy-to-get-wrong details left undocumented.

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

Purpose3/5

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

The verb 'clamp' plus 'tail observations' and 'order-statistic boundaries' does describe winsorization, but the description never uses the canonical term 'winsorize' that the title and a user query would use, and it draws no distinction from siblings such as bpj_series_quantile or bpj_series_min_max_scale. An agent can infer the transform but must work to match it against a request.

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

Usage Guidelines2/5

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

There is no guidance on when to apply this versus related siblings (quantile, min/max scaling, trimming), no mention of what a typical fraction value means in practice, and no stated preconditions. The agent is left to infer usage entirely from the verb.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.