Skip to main content
Glama

集客ファネルの詰まり診断 / Funnel bottleneck diagnosis

diagnose_funnel_bottleneck
Read-onlyIdempotent

Diagnose conversion bottlenecks using 2–10 named stage counts and an optional relative improvement percentage. Returns conversion rates, the lowest-rate transition, ranked final-stage gains and data cautions. 集客の改善候補を選ぶために段の名前・人数と改善率を入力し、通過率・最低の段・最後の人数の増分・注意点を返します。 Set language to 'en' for English output.

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": {
      "stages": "<stages>"
    },
    "name": "diagnose_funnel_bottleneck"
  }
}

Input Schema

NameRequiredDescriptionDefault
stagesYesOrdered funnel stages. / 上流から順に並べた段。
languageNoOutput language: ja (default) or en. / 出力言語。既定は日本語(ja)、英語はen。ja
improvement_percentNoRelative improvement percentage, 1–100; 10 means a 10% relative increase. / 相対改善率(1〜100)。10は現在の率を相対で10%改善。

Output Schema

NameRequiredDescriptionDefault
summaryYesCalculation assumptions and interpretation. / 計算の前提と結果の説明。
warningsYesData cautions and general reference thresholds. / データの注意点と一般的な目安。
bottleneckYesLowest-rate transition; earliest on ties, null if unavailable. / 最低通過率の段。同率は先の段。算出不可はnull。
transitionsYesConversion rates between adjacent stages. / 隣接する段の通過率。
improvementsYesIndependent improvement scenarios ranked by gain or reduction. / 増分または減少数の大きい順の独立した改善試算。
improvement_percentYesRelative improvement percentage used. / 試算に使った相対改善率。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the lower bar applies. The description still adds real behavioural content beyond them: it discloses that the analysis identifies the lowest-rate transition, ranks final-stage gains and emits 'data cautions'. It does not mention how non-monotonic or all-zero stage counts are handled, which is the main residual gap.

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?

The English purpose statement and output summary are front-loaded, and the bilingual repeat is functional given the ja/en language parameter rather than redundant padding. Length is proportionate to a three-parameter analytical tool, with only mild duplication between the English and Japanese sentences.

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

Completeness4/5

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

An output schema exists, so the description need not enumerate return fields, and full schema coverage removes parameter ambiguity. What remains missing is whether stages must be strictly ordered or monotonically decreasing for the conversion math to be meaningful — a semantic detail an agent would want before constructing input.

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%, and every parameter (stages, name, count, language, improvement_percent) is documented in the schema down to character-class and range constraints. The description restates '2–10 named stage counts' and 'optional relative improvement percentage' without adding syntax or ordering semantics beyond the schema, so the baseline 3 applies.

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?

Names a specific verb and resource ('Diagnose conversion bottlenecks') and immediately bounds the input shape (2–10 named stage counts plus an optional relative improvement percentage). It also states the analysis produced — conversion rates, lowest-rate transition, ranked final-stage gains, cautions — so the tool is distinguishable from a generic KPI or planning tool 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 Guidelines3/5

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

The Japanese sentence gives a use context ('to choose improvement candidates for acquisition'), which implies when the tool is appropriate. However, it never states when not to use it, nor does it contrast with the sibling tools (check_business_plan_assumptions, reverse_kpi_from_revenue_target), so the agent must infer the routing decision.

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.

Resources