KH Merch Graph

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

With no annotations, the description carries the full behavioral burden. It adds one important disclosure — results are candidates and actual availability is not guaranteed — but does not state whether this is read-only, whether results are paginated, or how many results are returned beyond the schema's limit parameter.

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?

Two short sentences with no wasted words. The core purpose is front-loaded, and the caveat immediately follows as relevant secondary information.

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 six-parameter tool with nested filtering and no output schema, the description covers the main filters and the key caveat. It leaves return-shape expectations vague beyond 'candidate SKU' and does not clarify how nested term filters combine with other filters.

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 schema already documents all six parameters including the nested terms object and enum values. The description mentions IP, character, budget, and purpose but omits terms and limit, adding little 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 states a clear verb and resource: searching the catalog for candidate SKUs matching IP, character, budget, and purpose. It distinguishes the tool from resolve_listing-style siblings by framing it as catalog discovery rather than listing resolution, though it does not name the alternatives.

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?

Usage is implied — search the catalog when you have conditions and want candidate SKUs — but there is no explicit when-to-use/when-not-to-use guidance or comparison with siblings such as resolve_listing. The caveat about availability is useful but is not an alternative-selection rule.

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 annotations exist, so the description carries the full burden. It does disclose the computed outputs (route-by-route totals and the cheapest route), which implies a read-only calculation with no side effects, but it never states that explicitly, nor mentions cost model assumptions, currency of results, rate limits, or what happens when neither weight_g nor sku_id is supplied.

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?

A single dense sentence with zero filler, and the input-to-output relationship is front-loaded. The parenthetical placement of '(or sku_id)' inside a long clause slightly hurts parseability but nothing is wasted.

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?

With no output schema, the description does the necessary work of naming what is returned (per-route totals and the cheapest route), and the input schema fully covers the parameters. It leaves the return structure unspecified (field names, whether all routes or only the best are returned) and omits the neither-weight-nor-sku_id case, so it falls just short of complete.

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 schema already documents all five parameters including the weight_g/sku_id fallback rule. The description reinforces the three primary inputs and the weight-or-sku_id alternative but adds no format, unit, or constraint details beyond what the schema provides. Baseline 3 applies.

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 output set: it returns per-route proxy×shipping total cost estimates plus the cheapest route, driven by listing price, weight (or sku_id), and destination country. That is far more than a restatement of the name 'estimate_landed_cost' and makes the tool's function unambiguous. No sibling (resolve_listing, explain_product, discover, report_correction) overlaps, but the description does not explicitly differentiate itself from them.

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 '(or sku_id)' phrasing implies the alternative input path for weight, which is useful selection guidance. However, there is no statement of when this tool should be chosen over alternatives, no prerequisites, and no exclusions — usage is only indirectly implied by the listed inputs.

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 annotations are provided, so the description must disclose behavioral traits itself. It reveals the kinds of data returned, but says nothing about read-only/non-destructive behavior, authentication, rate limits, error handling, or what happens when a query is ambiguous or when neither identifier is supplied.

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?

A single, front-loaded sentence with no filler; it states the input modes first and then the returned information, which is exactly the structure an agent needs.

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 lookup with no output schema, the description usefully enumerates the returned fields (product line, character, dimensions, resale history, source URL). However, it lacks the when-to-use routing and behavioral disclosure needed without annotations, leaving material gaps for an agent choosing among six sibling tools.

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%, and the schema already explains that sku_id and query are alternatives and that query is natural-language. The description repeats the either/or input modes but adds no syntax, format, or validation detail 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.

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

States a specific verb (返す, 'returns') and enumerates the resource details returned (product line, character, dimensions, resale history, source URL), which distinguishes it from generic listing tools. It does not explicitly name or contrast with siblings such as resolve_listing, so it stops short of a 5.

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 only notes that either a sku_id or a natural-language query may be supplied; it gives no guidance on when to choose this tool over resolve_listing, discover, or resolve_listings_batch, and no exclusions or prerequisites. Usage is implied at best through the purpose statement.

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?

With no annotations, the description carries the full behavioral burden. It mentions that a receipt ID is returned, but does not explain what happens after submission, whether the report is reviewed, whether it creates a pending change, or any auth/rate-limit constraints.

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 two short, front-loaded sentences with no filler. It is efficient, though extremely terse given the tool's workflow complexity.

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 schema fully documents the parameters and the description notes the receipt-ID return value. However, for a report-submission tool with no annotations and no output schema, it leaves important workflow and post-submission behavior unexplained.

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 all five parameters are already documented in the input schema. The description adds no additional meaning about field, sku_id, proposed_value, source_url, or note beyond what the schema provides.

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: reporting catalog errors or omissions. It is clearly different from siblings such as resolve_listing or explain_product, though it does not explicitly name alternatives.

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 no guidance on when to use this tool versus resolve_listing, resolve_listings_batch, or explain_product. It also omits prerequisites, exclusions, or workflow context for submitting a correction.

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 annotations are provided, so the description carries the full behavioral burden. It discloses the returned output categories, which is useful, but it does not state whether the tool is read-only, whether it writes or logs data, what happens with `url` or `src`, or whether there are rate limits or error behaviors.

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 a single tightly packed sentence that front-loads the input source and enumerates the outputs. There is no filler, and every element contributes to understanding what the tool returns.

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?

With six parameters, no annotations, and no output schema, the description should do more to explain return-value format, usage context, and behavioral constraints. It lists output categories but does not describe their structure or reliability, and it omits when to choose this tool over siblings.

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 schema itself documents all six parameters, including `src`, `url`, `platform`, `price_jpy`, and `description`. The description adds only broad meaning by implying title and description are used; it does not clarify how `platform` or `price_jpy` influence resolution, so baseline 3 is appropriate.

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 transformation: from Japanese used-listing title/description it returns candidate official SKU, condition terms, counterfeit warning, and list-price ratio. This is more than a tautology and names concrete outputs, but it does not distinguish the tool from the sibling `resolve_listings_batch` or explain when single resolution is preferred over batch.

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 no explicit when-to-use guidance, no exclusions, and no alternatives. It also does not state whether this is for single listings only, when to use it instead of `resolve_listings_batch` or `explain_product`, or what prerequisites exist.

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?

With no annotations, the description carries the behavioral burden well: it discloses the 5-item cap, order preservation between input and output, and the partial-failure shape ({ error } only for failed items). It stops short of stating whether the operation is read-only or what a successful element looks like beyond deferring to resolve_listing.

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?

Four short sentences, each carrying distinct information: what it does, when to use it, what comes back, and the two boundary cases (over 5, exactly 1). Front-loaded and waste-free.

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?

No output schema and no annotations, so the description must explain returns — it does, covering ordering and the error-element shape while deferring success-element format to resolve_listing. Adequate for correct invocation, though the success-element structure is only implied by reference.

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% and the single array parameter is fully documented down to per-field descriptions, so the schema does the heavy lifting. The description's note that results align to input order and that more than 5 must be chunked adds operational meaning, but 'same arguments as resolve_listing' repeats what the schema already says.

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?

States a specific action (batch-execute resolve_listing) with an explicit bound (max 5) and explicitly differentiates from the single-item sibling. An agent can tell exactly what this tool is versus resolve_listing without opening either 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?

Gives explicit when-to-use (querying many listings at once), an explicit fallback for the single-item case (use resolve_listing), and an explicit overflow rule (split into groups of 5 and call multiple times). No inference required.

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