Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

cross_feature_ab_report

Read-only

Ranks feature-branch variants by per-outcome performance and flags branches below the minimum outcome threshold, enabling clear A/B comparisons.

Instructions

Rank feature-branch variants by per-outcome performance.

Needs Kiln Pro.

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": {
      "feature_id": "<feature_id>"
    },
    "name": "cross_feature_ab_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
feature_idYesId of the feature whose branches are compared.
min_outcomes_per_branchNoThe fewest recorded outcomes a branch needs to be ranked; a branch with fewer is listed as excluded, with its sample size. Defaults to ``3``. Default: 3.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.5.1
    • addedInput schema / properties / feature_id / description
      Added value: +"Id of the feature whose branches are compared."
    • changedInput schema / properties / min_outcomes_per_branch / description
      Previous value: -"Default: 3."New value: +"The fewest recorded outcomes a branch needs to be ranked; a branch with fewer is listed as excluded, with its sample size.  Defaults to ``3``. Default: 3."
  2. Addedv1.5.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond that, the Kiln Pro tier requirement, but says nothing about what the ranking output contains or how excluded branches surface. Adequate but thin on top of the annotations.

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?

Two short sentences with the core action front-loaded and the prerequisite segregated on its own line. Nothing is wasted, though the second line could be merged or expanded slightly for smoothness.

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?

With no output schema, the description should hint at the return shape (ranked variants, excluded branches with sample sizes), which it omits. It is complete enough to invoke correctly given the rich parameter schema and annotations, but not complete enough to predict results.

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 description coverage is 100%, so feature_id and min_outcomes_per_branch are already fully documented including the default and the exclusion behavior. The description adds no syntax, format, or interpretation beyond the schema, which is the expected baseline when the schema does the work.

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

Purpose4/5

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

The description gives a specific verb ('Rank') and resource ('feature-branch variants') plus the ranking basis ('per-outcome performance'), so an agent knows this is a read-side A/B ranking report for feature branches. It does not name the near-identical siblings (cross_branch_ab_report, cross_preset_ab_report), so differentiation still requires inference.

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

Usage Guidelines3/5

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

Usage is implied by the phrase 'feature-branch variants,' but there is no explicit statement of when to pick this over cross_branch_ab_report or cross_preset_ab_report. The only gating guidance is the prerequisite 'Needs Kiln Pro.'

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

Deploy Server

Other Tools