UsedBikeCenter ZAMA バイク・原付の買取査定 (Japan motorcycle buyback)

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

The readOnlyHint annotation already signals a safe, non-destructive operation; the description adds useful context that no purchase application is created and that only a market-price estimate is returned. However, it mentions 「車両状態別」 (by vehicle condition) while the input schema exposes no condition parameter, leaving a behavioral gap about how condition affects the result.

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 front-loaded with the core function and then moves to trigger phrases, non-application behavior, and sibling routing. It is slightly long due to the enumerated user-phrase examples, but those examples genuinely help an agent recognize when to select the tool.

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?

For a simple two-parameter, read-only lookup with no output schema, the description covers what is returned, when to use it, and how to resolve ambiguous models. The main unresolved issue is the claimed condition-based pricing not being reflected anywhere in the input schema or explained further.

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 description coverage is 100%, so the baseline applies. The description mostly repeats the schema's guidance that model should use the official form from search_models and that maker is optional for narrowing. It adds little beyond what the parameter descriptions already state.

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 states a specific verb and resource: it returns approximate purchase prices in yen for used bikes, mopeds, and scooters. It also explicitly differentiates itself from siblings by noting that it only presents estimates and that actual applications go through submit_kaitori_request, while model disambiguation goes through search_models.

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 gives concrete trigger phrases like 「いくらになる」「相場は」「査定して」, clearly limits the tool to price estimation, and tells the agent to use submit_kaitori_request for actual applications and search_models first when the model is not identifiable. This is explicit when-to-use and when-not-to-use guidance.

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

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

No contradiction with readOnlyHint/openWorldHint/destructiveHint. Beyond those annotations, the description discloses that the tool normalizes fuzzy input to canonical model names, returns no price data, and is a mandatory pre-step for get_price. It does not detail return cardinality, but the added workflow/scoping context is substantial.

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 compact and front-loaded: purpose, acceptable input examples, exclusion, and prerequisite each get one sentence. There is minimal redundancy and no filler.

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?

For a simple read-only search tool with one parameter and no output schema, the description covers what, why, when, and how it relates to get_price. It could be more explicit about whether the result is a single canonical name or a list of candidates, but the overall flow is clear.

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?

The schema already documents the single query parameter with 100% coverage, but the description adds meaning by explicitly inviting ambiguous and partial inputs and supplying additional examples ('125のスクーター', '4ミニ', '原付'). This tells the agent it does not need a canonical model name to call the tool.

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 states a specific operation: search and identify formal motorcycle model names from user-provided manufacturer/model/type/displacement. It also disambiguates from the price tool by explicitly saying it does not return market prices (use get_price), so an agent can distinguish it from siblings.

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?

It says when to use it (to resolve ambiguous/partial input like 'CB400', '125のスクーター', '原付' into official model notation) and gives an explicit prerequisite: call it before get_price. It also tells the agent what not to use it for by pointing price-related needs to get_price.

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

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

Annotations are minimal (readOnlyHint=false, openWorldHint=true, destructiveHint=false), so the description carries the full behavioral burden and meets it. It discloses the critical consent contract — application contents must be shown and explicit agreement obtained before confirm=true — and the preview behavior when confirm=false. It also conveys that this triggers a real-world outbound purchase request, which is essential context for an agent.

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 long but every sentence earns its place: trigger conditions, exclusion rule, optional preferred date-time fields, and the mandatory consent workflow. The 【重要】 marker calls out the critical safety step. It is slightly dense and the consent warning sits toward the end rather than being front-loaded, but this length is justified for an 11-parameter real-world mutation tool.

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 invocation flow is thoroughly covered: when to trigger, what data to collect, optional fields, and the confirm/preview contract. The main gap is the post-success outcome — there is no output schema and the description never states what happens once confirm=true (what the tool returns or what the user should be told next), which an agent would benefit from knowing.

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 description coverage is 100%, so the baseline is 3. The description adds mild cross-parameter context — preferred_1~3 are optional up to the third choice, confirm=false returns a preview — but most of this is already present in the individual schema property descriptions (e.g., confirm already states 未確認なら false（プレビューが返る）). Little semantic value beyond the schema.

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 names a specific verb (申し込む/apply), a specific resource (無料の出張買取 for bikes/scooters/mopeds), and concrete user-intent triggers (「売りたい／申し込みたい／来てほしい／査定に来て／引き取ってほしい／廃車にしたい／処分したい」) that should fire this tool. It explicitly distances itself from get_price, allowing an agent to distinguish it from siblings 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.

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

Provides explicit when-to-use conditions via concrete user utterances and an explicit when-not-to-use rule naming the alternative: '単に相場を知りたいだけの段階では使わず、その場合は get_price を使うこと'. This leaves no ambiguity about tool selection and directly routes the agent to the correct sibling.

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