Skip to main content
Glama

plan_speech

Designs a voice and speaking style from a scene or use case, returning a reusable plan without generating audio. Use it to preview and lock a consistent voice before speech generation.

Instructions

用途・場面(scene)から、合う声と話し方を考える(音声は作らない・プレビュー用)。

generate_speech に同じ scene を渡すと、ここで考えたプランがそのまま使われる (プランはキャッシュされ、同じ scene なら毎回同じ声になる)。 気に入らなければ replan=True で考え直すか、voice_description / style を直接指定する。

Args: scene: 音声を使う場面・用途・聞き手など(例: "AWS のイベントでのプレゼン。会場は数百人のエンジニア")。 text: 読み上げる予定の文章(任意。言語判定や雰囲気の参考にする)。 gender: 話者の性別を固定したい場合(任意。female / male / neutral)。 language_code: 言語を固定したい場合(任意。例: ja-JP)。 model: 読み上げに使う TTS モデル(任意。キャッシュの区別に使う)。 enhance_text: True なら text に間( 等)を入れた版も返す(言葉は変えない)。 replan: True ならキャッシュを使わずに考え直す。 project_id: プロジェクトID上書き(任意)。

Returns: voice_description(声の設計)/ style(話し方)/ gender / language_code / rationale(理由)/ cached(キャッシュ再利用か)/ enhanced_text(enhance_text=True のとき)

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": {
      "scene": "<scene>"
    },
    "name": "plan_speech"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
modelNo
sceneYes
genderNo
replanNo
project_idNo
enhance_textNo
language_codeNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the key non-obvious behaviors: no audio is produced, plans are cached, the same scene yields the same voice deterministically, replan bypasses the cache, and enhance_text adds pauses without changing wording. It does not cover auth/permission requirements or error behavior, which keeps it short of a 5.

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 description is front-loaded with purpose and the generate_speech relationship before the Args block, and each sentence carries information. The Returns block is somewhat redundant given an output schema exists, and the Args list is long, but nothing is filler.

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

Completeness5/5

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

For an eight-parameter tool with zero schema descriptions and no annotations, the definition covers purpose, when-to-use, every parameter's meaning, caching semantics, and return fields. An agent has everything needed to call it correctly on the first attempt.

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

Parameters5/5

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 and it does: all eight parameters are documented with purpose, optionality, example values (a concrete Japanese scene string, ja-JP), and the allowed gender values (female/male/neutral). It also explains non-obvious semantics such as model being used only for cache keying and project_id being an override.

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?

The opening line names a specific verb and resource: derive a voice/speaking-style plan from a scene, and explicitly negates audio generation ("音声は作らない・プレビュー用"). It also names the sibling generate_speech and states the relationship, so an agent can separate the two without opening a schema.

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

Usage Guidelines5/5

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

It states when to use this tool (preview/planning before synthesis), what happens downstream (the same scene passed to generate_speech reuses the plan), and the two escape hatches when the result is unsatisfactory: replan=True or specifying voice_description/style directly. Alternatives are explicit rather than implied.

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