Japan RuleWatch

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

With no annotations, the description carries the full burden and does meaningful work: it states the output is concise, names included content (official URLs, scope limits), and explicitly excludes legal-compliance verdicts. This goes beyond the schema, though it does not discuss errors, authentication, or side effects.

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 front-loaded sentence that conveys action, input source, output contents, and a limiting constraint with no filler or redundancy.

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, read-style tool with no output schema, the description explains the input source, output nature, included content, and a key exclusion. A little more detail about the pack's structure or format would improve completeness, but it is sufficient for correct invocation.

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 fully describes 'id' as 'Exact rule ID returned by search_rules' with 100% coverage. The description restates this source constraint without adding format details, examples, or additional meaning 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 uses a specific verb ('Return') and names a concrete resource ('evidence pack') for a single rule ID. It also names the input source ('returned by search_rules'), which distinguishes it from the sibling search_rules tool.

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 indicates when to use the tool: after obtaining a rule ID from search_rules, and only for one rule at a time. It does not enumerate when not to use it, but the contextual dependency on search_rules is explicit.

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 provided, the description carries the full burden and does meaningful work: it reveals the index is 'small' and 'curated', clarifies the source type, and explicitly warns that results are 'evidence pointers, not legal conclusions'. This sets appropriate expectations about scope and result nature, though it omits operational details like rate limits or failure modes.

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 sentences with no filler. It front-loads the core purpose, immediately provides workflow guidance, and closes with an important caveat about output semantics. Every sentence 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?

The description communicates purpose, sequence, and the conceptual nature of results, but there is no output schema and no annotation support. It does not describe the actual shape of an 'evidence pointer' or explain how limit affects results, leaving meaningful gaps for a tool with no output schema.

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 only 50%, and the description adds no parameter-level meaning. The query parameter has a schema description, and the limit has min/max/default constraints, but the description does not compensate for the low coverage or clarify how the limit parameter behaves in the search context.

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 action ('Search'), a precise resource ('a small curated index of official Japanese sources'), and a domain ('mail-order sales advertising'). It also distinguishes itself from the sibling tool by framing itself as a search step rather than an evidence-gathering step.

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 instructs the agent to use this tool before get_evidence_pack, providing clear sequential guidance. It does not, however, articulate when not to use it or describe alternative conditions, so it stops short of full exclusion guidance.

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