Japan CAA Commercial Transactions Actions

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

Annotations only declare readOnly and openWorld, so the description carries most of the burden and does well: it discloses sort order (latest first), one-record-per-company-per-action deduplication, and that the payload includes service-observed diffs (actions added, changed, removed from the CAA list). The change-tracking disclosure is genuinely useful behavior an agent could not get from the schema. It loses a point for not stating pagination or how to retrieve records beyond the 200 cap.

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 question-style opening is front-loaded and immediately frames the query the tool answers, with the field list and caveats following in a logical order. The single long sentence that enumerates returned fields is dense and drags, though no sentence is genuinely 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?

With an output schema present, 100% parameter coverage and annotations set, the description only needs to add scope and behavior — and it does, via national-only scope, ordering, dedup semantics and change tracking. Remaining gaps are pagination behavior past the limit cap and its relationship to caa_action_lookup, both minor against an otherwise rich definition.

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%, including the default of 365 days ago and the 1-200 limit range, so the input schema already documents all three parameters. The description only echoes them ("since a date", "optionally filter by action_type") without adding format, semantics, or interaction detail. Baseline 3 is the correct ceiling here.

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 regulator, a specific statute, the resource (companies acted against) and the record granularity ("one record per company and action, latest first"). That is far more than a restated title. It stops short of 5 because it never distinguishes itself from the sibling caa_action_lookup, which an agent could plausibly pick for the same question.

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 supplies real scope constraints — "National actions only" and an optional action_type filter — which tell the agent when this tool's output is appropriate. What is missing is any routing guidance against the sibling caa_action_lookup or any note on when a date window is too broad. Usage is inferable but not spelled out.

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 already cover read-only and open-world safety, yet the description adds real behavioral context: the three possible statuses including 'not_found_in_checked_records (with checked_scope)' and 'unknown', plus the explicit caveat that matching is by name and location alone. This discloses the false-negative risk an agent needs for interpretation, though provenance handling (SHA-256, retrieved_at) is only named, not explained.

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?

Front-loaded with the core question, then inputs, then return fields, then status vocabulary — a logical order with essentially no filler. The return-field enumeration is somewhat list-heavy and partially redundant with the output schema, but it is compact.

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 read-only, single-entity lookup with a full schema and an output schema, the description covers purpose, inputs, matching limits, and status outcomes. Enumerating return fields overlaps with the output schema, and the meaning of 'unknown' versus the not-found status could be spelled out 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 coverage is 100%, so the baseline is 3, but the description adds that all three parameters are purely match keys ('matched by name and location only') and that the name must be Japanese. That framing gives the parameters meaning beyond their individual schema descriptions.

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 opens with a precise, answerable question — whether the CAA published a national action under the Act on Specified Commercial Transactions against a company with a given name. The verb/resource pair is specific and the singular 'lookup by company' framing distinguishes it from the sibling caa_action_list.

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 clearly states the input precondition (Japanese company name, optionally head office prefecture/municipality) and the matching constraint ('matched by name and location only'), which tells the agent when this tool will not find a record. It stops short of explicitly contrasting with caa_action_list, leaving that routing to inference from the names.

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 already declare readOnlyHint=true, so safety is covered. The description adds the content categories returned (prices, licensing, limits, freshness), which is useful context, but an output schema exists and would surface the same structure, so the incremental disclosure is modest.

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; every clause enumerates distinct payload content, so 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 parameters, a read-only annotation, and an output schema present, the description need not explain return values or safety. It is nearly complete for this simple tool; only a hint about when to reach for it is absent.

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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies under the '0 params' rule.

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?

Clear verb ("List") plus resource ("the tools of this server") and an enumeration of the payload contents (prices, data sources, licensing, daily limits, freshness). It is plainly distinguishable from siblings like get_receipt or drone_flight_check, though it does not explicitly name or contrast 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?

No explicit when-to-use or when-not-to-use guidance is given; usage is only implied by the discovery framing ("the tools of this server"). An agent can infer this is the entry point for learning available tools and pricing, but nothing states that intent directly.

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?

Beyond readOnlyHint=true, the description discloses pricing ('Free'), error behavior for unknown/unsettled ids (RECEIPT_NOT_FOUND), and a retention window (30 days after settlement). These are substantive operational facts an agent cannot get from the annotations or schema.

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?

Three short sentences, front-loaded with the purpose, followed by cost, error case, and retention. No sentence is redundant and nothing is buried.

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 an output schema present, return values need no explanation, and the annotations cover safety. The description still covers cost, failure mode, and data lifetime, leaving no material gap for an agent calling this single-param read tool.

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% and the schema already documents the 'rcpt_' + 64 hex format, so the baseline is 3. The description adds semantic constraint by implying the id must belong to a settled paid call, which goes slightly beyond the schema's format-only 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 opens with a specific verb+resource: 'Re-fetch the stored result of a settled paid call by its receipt_id.' This is unambiguous and an agent can immediately tell what the tool returns and what it operates on, even though the sibling tools are unrelated.

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 states the triggering condition clearly ('for when the response was lost after payment'), which is exactly the scenario that should select this tool. It also implicitly scopes usage to settled calls via the RECEIPT_NOT_FOUND note, though it names no alternative tools for other recovery paths.

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