Japan store verification for AI agents: stock, shelf price, opening status, and permitted photos.
Scored across 2 tools
The two tools are related but their boundaries are somewhat unclear. check_service_fit sounds like an eligibility check, yet its description says it is used when an AI needs someone to verify a fact, which overlaps with prepare_verification_request. An agent could reasonably confuse when to call which tool.
Both tool names use a consistent snake_case verb_noun pattern: check_service_fit and prepare_verification_request. The convention is predictable throughout the set.
With only two tools, the server feels thin for a domain that implies physical-world verification. While the narrow purpose may justify a small set, it is borderline under-scoped.
The tools cover fit checking and preparing a manual-review URL, but there is no way to submit the request, track status, or retrieve results. This leaves a significant gap for agents trying to complete an end-to-end verification task.
Cancel a request only while it is pending manual review or open. Claimed or completed work cannot be cancelled through this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| request_id | Yes | ||
| status_token | Yes |
Use when an AI needs someone on the ground in Japan to verify a current physical-world fact such as store stock, shelf price, opening status, or permitted photos, after web research or APIs are insufficient.
| Name | Required | Description | Default |
|---|---|---|---|
| location | Yes | Public business or retail location in Japan. | |
| objective | Yes | The physical-world fact that must be verified. | |
| evidence_requirements | No | Requested evidence such as photo, displayed price, stock observation, or timestamp. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare a safe, read-only, idempotent, open-world profile, so the bar is lower. The description adds meaningful context that a human agent is physically dispatched in Japan to observe facts, which is behavior not captured by annotations. It omits operational traits like turnaround time, cost, or what a response contains, keeping it at an adequate 3.
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 sentence that is tightly front-loaded with the trigger phrase 'Use when', followed by the condition and concrete examples. 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?
With three parameters fully described in the schema and annotations covering the safety profile, the main remaining gap is what the tool actually produces or triggers (e.g., dispatch of a verifier, expected response, relationship to prepare_verification_request). The description covers invocation conditions but not the outcome, leaving it merely adequate.
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 location, objective, and evidence_requirements are already documented in the schema, setting a baseline of 3. The description's examples of verifiable facts loosely map to the objective parameter but add no syntax, format, or constraint detail 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+resource: verify a current physical-world fact via someone on the ground in Japan. It goes beyond the vague name 'check_service_fit' by listing concrete examples (store stock, shelf price, opening status). It does not explicitly distinguish itself from its sibling prepare_verification_request, so it falls 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?
It gives an explicit precondition for use: 'after web research or APIs are insufficient', which tells the agent when this tool is warranted. However, it never names the alternative (prepare_verification_request) or states when-not to use it, so the routing guidance is incomplete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a retry-safe manual-review physical verification request in Japan. Reuse the same idempotency_key for the same logical request. No payment, worker hire, or fulfillment commitment is created automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| deadline | No | ||
| location | Yes | ||
| objective | Yes | ||
| constraints | No | ||
| idempotency_key | Yes | Stable key for this logical request. Reuse the same key when retrying create after a lost response. | |
| evidence_requirements | No |
Read the current request state and, when completed, receive structured observations and temporary signed evidence URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| request_id | Yes | ||
| status_token | Yes |
Prepare a Japan on-site verification request for a human-executed store check. Returns a prefilled manual-review URL only; it does not purchase, submit, hire, pay, or create a fulfillment commitment.
| Name | Required | Description | Default |
|---|---|---|---|
| deadline | No | Requested deadline in plain text or ISO 8601. | |
| location | Yes | Public business or retail location in Japan. | |
| objective | Yes | What must be physically verified. | |
| constraints | No | Constraints or actions the executor must not take. | |
| evidence_requirements | No | Evidence needed to consider the task complete. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuine value beyond that by stating the tool returns only a prefilled manual-review URL and creates no fulfillment commitment, clarifying that this preparation step has no 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?
Two tight sentences with the core action and the return value front-loaded, followed by the negative scope. No filler or repetition.
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 compensates by stating exactly what is returned (a prefilled manual-review URL) and what is not performed. Combined with 100% schema coverage and clear annotations, an agent has everything needed to call this correctly.
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 location, objective, deadline, constraints, and evidence_requirements are all fully documented in the schema. The description adds no parameter-level detail beyond what the schema already provides, making the baseline 3 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?
States a specific verb ('Prepare') and resource ('Japan on-site verification request for a human-executed store check'), plus the output form (prefilled manual-review URL). The purpose is unambiguous, though it never references or distinguishes itself from the sibling check_service_fit.
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 clear context for use (Japan on-site physical verification of a store) and explicit exclusions of adjacent actions ('does not purchase, submit, hire, pay, or create a fulfillment commitment'). However, it names no alternative tool, so the routing guidance among siblings is incomplete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
cancel_verification_requestcreate_verification_requestget_verification_statuscheck_service_fitprepare_verification_requestVerify live product price, currency, stock, variants and published shipping evidence for AI agents.
Verified location-bound retail evidence for AI agents, delivered by human field workers.
Product price checks and affiliate link building for AI shopping agents.
Japanese catalog of physical devices AI agents can control: connectivity ratings, APIs, sources.
Add one secure layer between your agents and this server.