中古バイク・原付・スクーターを売りたいユーザーに、車種と車両状態別の出張買取の概算相場（円）を返す。ユーザーが「いくらになる／相場は／売ったらいくら／査定して／高く売りたい／バイクを処分したい／乗らなくなった／不動車や事故車でも売れる?」等と尋ねた時に使う。相場の提示のみで、実際の買取申込は行わない（申込は submit_kaitori_request を使う）。車種が特定できない場合は先に search_models で正式表記を確定すること。
| Name | Required | Description | Default |
|---|---|---|---|
| maker | No | メーカー名（任意。同名車種の絞り込み用。例: ホンダ／ヤマハ） | |
| model | Yes | 車種名（search_modelsの結果の正式表記をそのまま渡す） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as readOnly and non-destructive. The description adds that it provides estimates only and does not submit purchase applications, which clarifies its limited scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at 4 sentences, front-loaded with the main purpose. Every sentence adds value: purpose, usage triggers, sibling distinction, and prerequisite step.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description mentions return value as approximate price in yen but does not specify the exact format or the role of the 'condition' parameter (which is not in schema). No output schema exists, so more detail on the return structure could be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameter details are already present. The description adds that 'model' must be the exact formal notation from search_models and provides example values for 'maker' (ホンダ／ヤマハ), adding practical usage guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns an approximate market price in yen for used motorcycles (バイク) based on model and condition. It uses specific verb '返す' and resource '概算相場', and distinguishes from siblings search_models and submit_kaitori_request by mentioning when to use each.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly lists user queries that trigger this tool (e.g., 'いくらになる' / '相場は'), and states that actual purchase requests should use submit_kaitori_request. It also instructs to use search_models first if the model is not identified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a distinct, non-overlapping function: search_models resolves model names, get_price provides price estimates, and submit_kaitori_request handles actual buyout requests. The descriptions explicitly cross-reference each other to prevent misuse.
All tool names follow a consistent verb_noun pattern (search_models, get_price, submit_kaitori_request). The use of 'kaitori' is domain-appropriate and does not break the naming convention.
Three tools is well-scoped for the narrow purpose of motorcycle buyback estimation and request submission. Each tool earns its place in the core workflow, and the count is neither too thin nor excessive.
The set covers the full user journey: model identification (search_models), price lookup (get_price), and final purchase request (submit_kaitori_request). The required confirmation step for the request is embedded, leaving no obvious dead ends or missing operations for the domain.
