Japan RuleWatch

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

With no annotations, the description carries the behavioral burden and does so well: it states the output's scope (concise pack), content (official URLs, scope limits), and an explicit limitation (no legal-compliance verdict). Absent side effects are not a concern for a retrieval tool, though read-only behavior is not named.

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 front-load the primary action and scope, then append the content and the critical limitation. Every clause earns its place with 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 one-parameter retrieval tool with no output schema, the description gives enough context about what the result contains and what it deliberately omits. It is slightly light on the exact shape of the returned evidence pack, but this is a minor gap.

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 input schema already documents the only parameter as 'Exact rule ID returned by search_rules', and the description repeats that same relationship without adding format, type, or usage nuance. With 100% schema coverage, the baseline of 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 identifies a specific action (Return), a specific resource (a concise evidence pack), and a precise input scope (one rule ID returned by search_rules). It also states what the pack includes, making the tool distinguishable from search_rules.

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 clearly situates the tool after search_rules by requiring a rule ID returned by that sibling, so an agent knows when to call it. It lacks an explicit 'do not use when...' statement, but with only one sibling the routing is unambiguous.

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 burden of behavioral disclosure. It does disclose that the tool is informational evidence and 'not a legal verdict,' which is useful framing, and it enumerates the categories of returned data. However, it does not mention side effects, authentication needs, data freshness limitations, or any behavior beyond returning a list.

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 efficient, using two sentences to cover output scope and an important legal disclaimer. The first sentence is dense but packs meaningful detail. No filler or redundant phrasing is present.

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?

Given the tool has no annotations, no output schema, and minimally documented boolean parameters, the description leaves significant gaps: input semantics, supported parameter combinations, and what the response structure looks like. It does explain the output categories at a high level, but an agent would struggle to know which parameter values to pass for a given scenario.

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 input schema has 4 boolean parameters with 0% description coverage, and the tool description never mentions them. It does not explain how collectsTravelPayment, actsAsContractingParty, handlesCancellationOrRefund, or acceptsReservationOnPlatform influence the A/B/C flow or the returned evidence pack. The description completely fails to compensate for the schema's lack of parameter documentation.

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 a specific verb ('return') and a well-defined resource: official Japanese primary-source URLs, evidence locations, checked dates, source versions, requirements, traveler-screen checks, and re-check triggers. It is easy to tell what output this tool produces. It does not explicitly distinguish itself from the sibling get_tourism_preflight, though the mention of a 'complete supported A/B/C flow' hints at a broader scope.

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 guidance about when to use this tool versus get_tourism_preflight or search_rules. The 'Paid:' prefix signals a commercial condition, but there is no stated context, prerequisite, or exclusion. Usage must be inferred from the listed output contents rather than explained.

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 burden and does disclose several behaviors: it's free, it classifies into an A/B/C model, lists missing facts, flags manual review, and explicitly does not return primary-source evidence. However, there is no mention of output shape, error behavior, or how the input booleans drive the classification.

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 clean sentences with the core action front-loaded and a clarifying negative in the second sentence. The leading 'Free:' is slight noise, but overall every clause earns its place.

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 tool with four inputs, no output schema, and no annotations, the description omits the definition of the A/B/C model, the input-to-classification mapping, and the returned shape of the missing-facts and manual-review results. An agent can call it but cannot accurately predict its output.

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 0%, so the description must compensate for the four boolean parameters, but it never mentions them or explains how they map into the A/B/C decision. The parameter names are self-descriptive, but nothing ties the inputs to the classification output.

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 uses specific verbs (classify, list, flag) against a named resource (Japan-bound hotel service flow) and states the output kinds (A/B/C classification, missing facts, manual-review flags). The explicit negative — 'does not return primary-source evidence' — further delineates what the tool is for.

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 offers no guidance on when to use this tool versus alternatives, no when-not-to-use conditions, and no prerequisites. 'Free:' hints at a cost comparison but never states a selection context, leaving the agent to infer suitability.

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 transparency burden and does so well: it discloses the index is 'small' and 'curated,' restricts sources to 'official Japanese sources,' and warns that results are 'evidence pointers, not legal conclusions.' It does not describe exact result formatting, but covers the key behavioral expectations for a search tool.

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 three short sentences with every sentence earning its place: what it searches, when to use it, and how to interpret results. It is front-loaded with the core purpose.

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 search tool with no output schema, the description is complete enough: it states the domain, scope, usage order, and the nature of the results. The query parameter is documented in the schema, and the 'evidence pointers' statement gives the agent a clear expectation of the return value.

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 50%, with the query parameter already documented as 'Japanese or English search terms, maximum 200 characters.' The limit parameter has no description but its default, minimum, and maximum are clear from the schema. The tool description adds little parameter-specific meaning beyond the structured 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 and resource: 'Search a small curated index of official Japanese sources about mail-order sales advertising.' It also distinguishes itself from the sibling by stating it is a precursor to get_evidence_pack and that results are evidence pointers, not legal conclusions.

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 explicit sequencing guidance: 'Use this before get_evidence_pack.' This tells the agent when to invoke this tool relative to the only sibling, and clarifies that the output is meant as input evidence for later steps.

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