Average processing days of Japan residence applications per status, from ISA's published PDFs.
Scored across 5 tools
Each tool targets a distinct need: catalog describes the service itself, get_receipt recovers lost paid responses, statuses enumerates valid inputs, and latest vs. history split cleanly into current-figure vs. time-series queries. The descriptions explicitly delineate inputs and return shapes, leaving little room for misselection.
The three domain tools share a clear residence_processing_* prefix, but catalog is a bare noun and get_receipt uses a verb_noun form, so conventions are mixed. Names remain readable and the prefix grouping helps, but there is no single predictable pattern.
Five tools is well-scoped for a narrow data-lookup service: one discovery tool, two query tools, plus catalog and receipt recovery. Every tool has an evident role with no filler.
The surface covers discovery, latest value, historical series, pricing/limits, and paid-call recovery, which is solid lifecycle coverage for a read-only data API. Minor gaps exist (e.g., no cross-status comparison or arbitrary period lookup), but agents can work around them by chaining history calls.
List the tools of this server with prices, data sources, licensing, daily limits and data freshness.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| legal | Yes | |
| terms | Yes | URL of the terms of service. |
| tools | Yes | Every tool of this server with its price. |
| paused | Yes | Operator pause flags (true = paused). |
| server | Yes | |
| payment | Yes | |
| provenance | No | Freshness receipts for every upstream source used. |
| daily_limits | Yes | Daily limits of paid calls (calls, usd, timezone) or a misconfiguration notice. |
| fetch_status_values | No |
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.
Re-fetch the stored result of a settled paid call by its receipt_id, for when the response was lost after payment. Free. Unknown or unsettled receipt ids return RECEIPT_NOT_FOUND. Results are kept for 90 days after settlement.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt_id | Yes | The receipt_id returned with a paid result ("rcpt_" + 64 hex characters). |
| Name | Required | Description |
|---|---|---|
| tool | Yes | Name of the paid tool that produced the result. |
| terms | Yes | URL of the terms of service. |
| result | Yes | The stored result, exactly as returned by the paid call. |
| payment | Yes | |
| provenance | Yes | Freshness receipts for every upstream source used. |
| receipt_id | Yes | Receipt id of the settled paid call ("rcpt_" + 64 hex). Use with get_receipt. |
| settled_at | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well past readOnlyHint=true by disclosing cost ('Free'), the failure mode and error code (RECEIPT_NOT_FOUND for unknown/unsettled ids), and the retention window (90 days after settlement). These are exactly the runtime traits an agent needs before calling.
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 action and the receipt_id, followed by behavioral facts. No filler, no restatement of the title.
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?
An output schema exists, so return values need no explanation, and the description still covers cost, error behavior, and retention limits. Nothing an agent needs to call this correctly is missing.
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% and the schema already specifies the receipt_id format ('rcpt_' + 64 hex characters, maxLength 80). The description only names the identifier without adding format or constraint detail, so the schema does the real work.
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 ('re-fetch'), specific resource ('stored result of a settled paid call'), and the keying mechanism ('by its receipt_id'). The 're-fetch ... for when the response was lost' framing clearly separates it from the unrelated sibling tools.
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 an explicit triggering scenario: use it when a paid call's response was lost after payment. It also implies the boundary condition (unknown or unsettled ids are not valid targets), but does not name an alternative tool or state a when-not clause for other lookup paths.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How has ISA's average processing time for this status of residence changed over time? Give status and optionally procedure and measure. Returns series per granularity (monthly from October 2024, quarterly FY2017 to FY2024 Q2, never mixed or interpolated), procedure and measure, oldest first, with periods that could not be read or are blank listed as gaps with the reason.
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | Status of residence: key (e.g. engineer-humanities-international, student, highly-skilled-professional-1a), Japanese name as in ISA's table (e.g. 留学, 高度専門職1号イ) or English name (e.g. Student). Exact match only; see residence_processing_statuses | |
| measure | No | Optional: disposition (days to issuance or notification of permission) or review_end (days to the end of examination; extension and change, from FY2020). Omit for both | |
| procedure | No | Optional: coe (certificate of eligibility), extension (extension of period of stay) or change (change of status of residence). Omit for all |
| Name | Required | Description |
|---|---|---|
| query | Yes | |
| terms | Yes | URL of the terms of service. |
| series | Yes | One series per granularity, procedure and measure, oldest first. Monthly and quarterly series are separate; nothing is interpolated. |
| source | Yes | Where the answer comes from: ISA's list page and PDF, and when this service read them. |
| status | Yes | |
| disclaimer | Yes | Read first: averages of applications approved in the period, as published by ISA; not a forecast for any individual application. |
| provenance | Yes | Freshness receipts for every upstream source used. |
| answered_at | Yes | |
| attribution | Yes | |
| fixed_notes | Yes | Notes that apply to every figure (approvals only, what disposition means, blank is not zero, seasonal peaks). |
| status_note | Yes | |
| history_note | Yes | |
| legal_notice | Yes | |
| residence_status | Yes | |
| latest_official_period | Yes | ISA's latest period on the list page and whether this service could read its PDF. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnly and openWorld, so the description usefully adds real behavioral contract: granularity boundaries (monthly from Oct 2024, quarterly FY2017–FY2024 Q2, never mixed or interpolated), oldest-first ordering, and that unreadable or blank periods surface as gaps with a reason. It does not say what happens with an unmatched status value, which is the main remaining gap.
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 sentences, front-loaded with the question the tool answers, then the output contract with the key constraints. Dense but each clause (granularity, ordering, gaps) conveys a distinct behavioral fact; only the 'Give status and optionally...' clause is 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, return formatting need not be explained, and the description still covers granularity, ordering, gap reporting, and optional dimensions. Nothing an agent needs in order to call this correctly and interpret the series is missing.
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% and includes enum values and examples, so the schema already carries this load. The description merely restates required/optional status and omits any enumeration or format guidance beyond the schema; baseline 3 applies.
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 specific resource and scope: historical average processing time series for a given status of residence, broken out by procedure and measure. An agent can distinguish this from residence_processing_latest by the explicit 'changed over time' / 'Returns series' framing, though the sibling is never named.
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?
'Give status and optionally procedure and measure' implies how to call it, and the time-series framing implies when to use it, but there is no explicit when-to-use statement or routing to alternatives. It never says to use residence_processing_latest for current figures or residence_processing_statuses to resolve keys — the latter hint lives only in the schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How many days did ISA take on average, in its latest published period, to process a residence application for this status of residence? Give status (key, Japanese or English name), optionally procedure. Returns figures with period, blank cells, the PDF's notes, ISA's PDF URL and retrieval time. Status: found, not_listed (blank, not zero), unknown, unreadable_latest (older readable period, labelled). Averages of approved applications, not a forecast.
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | Status of residence: key (e.g. engineer-humanities-international, student, highly-skilled-professional-1a), Japanese name as in ISA's table (e.g. 留学, 高度専門職1号イ) or English name (e.g. Student). Exact match only; see residence_processing_statuses | |
| measure | No | Optional: disposition (days to issuance or notification of permission) or review_end (days to the end of examination; extension and change, from FY2020). Omit for both | |
| procedure | No | Optional: coe (certificate of eligibility), extension (extension of period of stay) or change (change of status of residence). Omit for all |
| Name | Required | Description |
|---|---|---|
| query | Yes | |
| terms | Yes | URL of the terms of service. |
| answer | Yes | |
| source | Yes | Where the answer comes from: ISA's list page and PDF, and when this service read them. |
| status | Yes | found = figures in the latest period read; not_listed = blank cells in that period (not zero); unknown = no readable data yet; unreadable_latest = ISA's latest PDF could not be read, older_readable has the most recent readable period (older). |
| disclaimer | Yes | Read first: averages of applications approved in the period, as published by ISA; not a forecast for any individual application. |
| provenance | Yes | Freshness receipts for every upstream source used. |
| answered_at | Yes | |
| attribution | Yes | |
| fixed_notes | Yes | Notes that apply to every figure (approvals only, what disposition means, blank is not zero, seasonal peaks). |
| status_note | Yes | |
| legal_notice | Yes | |
| older_readable | Yes | Only with unreadable_latest: the most recent period this service could read. Older than ISA's latest. |
| residence_status | Yes | |
| latest_official_period | Yes | ISA's latest period on the list page and whether this service could read its PDF. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnly/openWorld annotations by disclosing response shape (period, blank cells, PDF notes, PDF URL, retrieval time) and, critically, the semantics of each status value: not_listed means blank rather than zero, and unreadable_latest falls back to an older readable period with a label. 'Averages of approved applications, not a forecast' heads off a likely misinterpretation.
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 returns, then status semantics — a sensible ordering. The latter half is telegraphic and dense ('Returns figures with period, blank cells, the PDF's notes...'), but no sentence 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?
An output schema exists, yet the description still clarifies the non-obvious parts: status-value semantics and that figures are historical averages. The main residual gap is routing guidance relative to the history sibling, which an agent must infer from 'latest published period'.
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 both enums are documented in-schema, so the baseline is 3. The description restates what status accepts and that procedure is optional, but adds nothing about the measure parameter (disposition vs review_end) beyond what the schema already says.
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 opening question states a precise verb and resource: average days ISA took to process a residence application for a given status, scoped to the latest published period. The 'latest published period' qualifier implicitly separates it from residence_processing_history, though no sibling is named explicitly.
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?
Usage is implied by 'Give status (key, Japanese or English name), optionally procedure', but there is no explicit statement of when to pick this tool over residence_processing_history or residence_processing_statuses. The pointer to residence_processing_statuses for valid keys lives in the parameter schema, not the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Which statuses of residence and procedures do ISA's processing-time tables cover, and which keys and names does this service accept? Returns the canonical list (key, Japanese and English names), procedures and measures.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| terms | Yes | URL of the terms of service. |
| statuses | Yes | |
| disclaimer | Yes | Read first: averages of applications approved in the period, as published by ISA; not a forecast for any individual application. |
| procedures | Yes | |
| answered_at | Yes | |
| attribution | Yes | |
| fixed_notes | Yes | Notes that apply to every figure (approvals only, what disposition means, blank is not zero, seasonal peaks). |
| legal_notice | Yes | |
| matching_note | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that the result is a canonical list of keys with Japanese and English names, plus procedures and measures — useful context, though the output schema already carries the return shape.
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 sentences: the first scopes what the tables cover, the second states what is returned. Front-loaded, no filler, and the key/name detail lands before the return summary.
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 zero parameters and an output schema present, the description needn't spell out return values or input semantics. It gives enough context (ISA processing tables, canonical keys, bilingual names) for an agent to know what this enumeration yields.
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. The mention of accepted keys/names refers to returned values, not inputs.
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 specific resource — the statuses of residence and procedures covered by ISA's processing-time tables — plus the canonical keys/names the service accepts. That is a clear verb-free but concrete lookup purpose. It does not distinguish itself from siblings such as residence_processing_history or residence_processing_latest, which is the only thing keeping it from 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?
Usage is only implied: asking 'which keys and names does this service accept' hints that this is a discovery/enumeration call to run before querying history or latest. There is no explicit when-to-use, when-not-to-use, or named alternative.
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.
catalogget_receiptresidence_processing_historyresidence_processing_latestresidence_processing_statusesAustralian SkillSelect EOI, invitation, nomination and processing-time data. No raw data.
PERM, prevailing wage and H-1B case status, DOL's queue and the visa bulletin, from federal records
Australia's official visa processing times per subclass and stream, with change alerts.
Japan business days & holidays (official Cabinet Office data). Free tool + x402 USDC paid tools.
Add one secure layer between your agents and this server.