jp-m2m-gateway

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

Despite no annotations, the description fully discloses the paid nature (0.05 USDC via x402), the HTTP 402 response, and the beta settlement process. This is transparent about the cost and response behavior, exceeding minimal requirements.

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 efficient sentences front-loading core purpose and payment info. While the beta note is slightly extraneous, the structure is clear and each sentence adds value.

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 no annotations or output schema, the description covers the tool's purpose, payment mechanism, and immediate response. However, it lacks details on post-payment data format or error handling, leaving minor gaps.

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?

With 100% schema coverage, the parameter 'corporate_id' is already well-defined. The description adds no additional meaning, justifying a baseline score of 3.

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 the tool retrieves statutory financial disclosure raw text blocks from gazette page scans via a Vision LLM. This specific verb+resource combination distinguishes it from sibling tools like get_government_records or get_pension_headcount_log.

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 guidance on when to use this tool versus alternatives. Does not mention prerequisites or exclusions, leaving the agent without context for selecting this tool over siblings.

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 full burden. It reveals that data is 'live,' 'pulled on demand,' and includes attribution, but does not disclose potential side effects, rate limits, data volume, or whether the operation is read-only. It is adequate but not comprehensive.

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 compact sentences, front-loaded with key information ('FREE during beta,' 'returns live data,' 'un-aggregated'). Every element adds value with no wasted words.

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 tool has no output schema, so the description should explain return values. It mentions 'procurement contracts, subsidy grants and certifications' but does not describe the structure or format of the data. This is a notable gap for completeness.

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 100% coverage, with corporate_id well described. The description adds context about the source (gBizINFO) and the type of data returned, which helps the agent understand how the parameter connects to the output. It goes beyond the schema alone.

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 it returns 'un-aggregated procurement contracts, subsidy grants and certifications' from gBizINFO. The verb 'returns' and the specific data types make the purpose explicit and distinct from sibling tools which focus on other data (e.g., get_gazette_financials).

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 mentions 'FREE during beta — returns live data,' implying it is for on-demand raw logs, but does not specify when not to use it or provide alternatives among sibling tools. No explicit usage guidance is given.

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. It discloses the paid nature, the 402 challenge, the receipt upon settlement, and the beta access unlocking. This is transparent about the core behavior, though it doesn't confirm read-only or destructive nature (likely read).

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 purpose, then adds essential context (payment, return format, beta status). It is slightly lengthy but each sentence provides unique value.

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 complexity (paid, beta, raw log), the description covers payment mechanism, return type, and beta terms. No output schema exists, so missing output details is acceptable. It provides sufficient context for an agent to understand usage and consequences.

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?

There is one parameter (corporate_id) with 100% schema description coverage (13-digit Japanese corporate number). The description adds meaning by linking the parameter to insured headcount data, enhancing 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 clearly states 'Un-aggregated month-over-month insured headcount deltas (健康保険・厚生年金) for one Japanese corporate number,' specifying the verb (get raw log), resource (pension headcount), and scope (per corporate number). This distinguishes it from siblings like get_gazette_financials which deal with financial data.

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 includes payment context ('each call costs 0.05 USDC') and the return behavior ('HTTP 402 payment challenge'), which guides usage. However, it does not explicitly state when not to use this tool or compare with alternatives beyond the payment model.

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 must fully disclose behavioral traits. It mentions pricing (0.05 USDC per call) and that the lookup is free, indicating a read-only, non-destructive action. However, it omits details like authentication requirements, error handling for invalid corporate numbers, rate limits, or the nature of the returned data beyond an api_url.

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 consists of two sentences that efficiently communicate the tool's nature and usage. The lead phrase 'Free catalog lookup' immediately sets expectations. Each sentence serves a purpose: identifying the action and providing guidance. A minor improvement would be to separate pricing into a note, but overall it is well-structured.

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 listing tool with one parameter and no output schema, the description covers the core function, pricing, and next steps. It lacks details about the output structure (e.g., list format, fields) but the reference to api_url partially compensates. Overall, it is adequate for an agent to understand the tool's role in the workflow.

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 for corporate_id has 100% coverage and already describes it as a '13-digit Japanese corporate number.' The description merely restates this as 'one Japanese corporate number,' adding no new semantic information about format, constraints, or examples. Baseline of 3 is appropriate given high schema coverage.

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 that the tool 'Lists the raw regulatory datasets available for one Japanese corporate number,' which identifies the specific action and resource. It also calls it a 'catalog lookup,' distinguishing it from data retrieval tools. However, it does not explicitly contrast with sibling tools like get_gazette_financials or search_corporations, missing a clear differentiation.

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 advises to 'Use the dataset tools or the returned api_url to retrieve data,' implying the tool is for listing only. It does not specify when to use this tool versus alternatives such as search_corporations or other get_* tools, nor does it mention any prerequisites or exclusions.

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 full burden. It mentions 'FREE — returns live data,' which is a useful behavioral trait. However, it does not disclose any limitations, auth needs, or error behavior, leaving some gaps.

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 extremely concise with two sentences: one stating the key benefit and another explaining the output usage. Every sentence is purposeful and front-loaded.

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 low complexity (2 parameters, no output schema), the description is complete. It explains what the tool does and how to use the result with dataset tools. The schema covers parameter details.

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 no additional information beyond what the schema provides for the parameters.

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 the tool's purpose: searching Japanese corporations by name and resolving them to 13-digit corporate numbers. It distinguishes itself from sibling tools which focus on other specific data types like financials or government records.

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 implies usage context by stating 'Use the corporate number with the dataset tools.' It does not explicitly list when not to use or alternatives, but the sibling tool names and distinct purpose provide sufficient guidance for an AI agent.

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