Reviewed public-data search and execution with provenance and verifiable integrity receipts.
Scored across 3 tools
Each tool targets a distinct concern: execute retrieves data via a contract, search_data queries metadata, and verify checks integrity receipts. No overlap or ambiguity between them.
All tool names are lowercase snake_case with a verb-first style (execute, search_data, verify). While not strictly verb_noun, the naming is predictable and consistent, though a less uniform pattern than the calibration example.
Three tools is a well-scoped set for a public data catalog: search, retrieve, and verify. Each tool serves a necessary role with no bloat or missing core functionality.
The domain covers discovering, accessing, and validating public data. search_data finds datasets, execute retrieves them, and verify ensures integrity—covering the full workflow without obvious gaps.
Run one allowlisted, bounded HTTPS GET contract and return extracted values, provenance, and an integrity receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| recipeId | Yes | ||
| parameters | No |
| Name | Required | Description |
|---|---|---|
| status | Yes | |
| receipt | Yes | |
| results | Yes | |
| question | Yes | |
| recipe_id | Yes | |
| elapsed_ms | Yes | |
| parameters | Yes | |
| provenance | Yes | |
| request_url | Yes | |
| retrieved_at | Yes | |
| interpretation | Yes | |
| contract_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and non-destructive behavior. The description adds that it is a bounded HTTPS GET and returns specific items, providing some context beyond annotations. However, it does not disclose auth requirements, rate limits, or potential side effects (though none expected).
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?
Single sentence with efficient wording, no redundancy. All necessary high-level information is front-loaded without extraneous details.
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 presence of an output schema and a single required parameter, the description is partially complete. However, it omits explanation of the optional parameters object and does not describe the output in detail. The existing output schema partially compensates, but the lack of parameter semantics is a notable gap.
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 0%, yet the description provides no explanation of the two parameters (recipeId and parameters). The meaning of recipeId is somewhat inferable from the tool's name and title, but the parameters object and its constraints are unexplained. The output schema exists but is separate; this is a gap.
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?
Description clearly states the action (execute), resource (retrieval contract), constraints (allowlisted, bounded, HTTPS GET), and outputs (extracted values, provenance, integrity receipt). It distinguishes from siblings by describing a specific execution action as opposed to search or verify.
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?
Description implies usage for executing a contract but does not provide when-to-use or when-not-to-use guidance relative to siblings search_data and verify. No explicit exclusions or alternative selection criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search current metadata from e-Gov Data Portal and Statistics Dashboard, then return a short ranked list with publisher, formats, coverage, usage terms, and official links.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Search all sources, downloadable datasets, or statistical series | all |
| limit | No | ||
| query | Yes | What data to find, preferably in Japanese |
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| query | Yes | |
| total | Yes | |
| status | Yes | |
| results | Yes | |
| sources | Yes | |
| available | Yes | |
| searched_at | Yes | |
| interpreted_as | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare it read-only, open-world, and idempotent. The description adds value by specifying data sources ('current metadata from e-Gov Data Portal and Statistics Dashboard') and the output format ('short ranked list with publisher, formats, coverage, usage terms, and official links'), which goes beyond annotation hints.
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?
Single sentence, front-loaded with the primary action, and every phrase adds specific information (sources, output characteristics). 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?
With a read-only search tool and an existing output schema, the description adequately covers functionality and return fields. However, it omits any mention of result limitations, no-results behavior, or default ranking, which would make it more self-contained.
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 only 67% (query and kind described, limit missing). The description does not compensate by explaining parameter usage or the limit parameter, nor does it clarify search language preferences beyond what the schema already provides.
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 ('Search') and identifies the exact resources (e-Gov Data Portal and Statistics Dashboard) and output structure (ranked list with publisher, formats, coverage, usage terms, links). This clearly distinguishes it from sibling tools like 'execute' and 'verify'.
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 is provided on when to choose this tool over others. The description does not mention alternatives, exclusions, or use-case context despite having sibling tools (execute, verify) in the same namespace.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check receipt and result hashes plus the execution envelope against the reviewed catalog. This detects later modification; it does not prove publisher authenticity or current freshness.
| Name | Required | Description | Default |
|---|---|---|---|
| execution | Yes |
| Name | Required | Description |
|---|---|---|
| valid | Yes | |
| checks | Yes | |
| receipt_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond annotations by clarifying that the tool detects modification but does not verify authenticity or freshness. Annotations already indicate readOnly, idempotent, non-destructive, and no contradiction is present.
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 concise sentences with no redundant information, front-loaded with the action and followed by important limitations. Every 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 the presence of an output schema (not shown), the description does not need to explain return values. It covers purpose, limitations, and input semantics adequately, though more detail on the input object structure would improve 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?
With 0% schema description coverage, the description partially compensates by mentioning 'receipt and result hashes plus the execution envelope', but the input object structure is not fully explained. Baseline for single parameter with low coverage is 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 title 'Verify an execution receipt' and description 'Check receipt and result hashes plus the execution envelope against the reviewed catalog' provide a specific verb and resource, clearly distinguishing it from sibling tools 'execute' and 'search_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 explicitly states what the tool does not do ('does not prove publisher authenticity or current freshness') and its purpose (detect later modification), guiding the agent on when to use it. However, it does not explicitly mention alternatives.
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.
search_data2 fields changedOutput schema / properties / interpreted_asAdded value: +{
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Output schema / requiredPrevious value: -[
- "status",
- "query",
- "searched_at",
- "results",
- "total",
- "available",
- "sources",
- "note"
-]New value: +[
+ "status",
+ "query",
+ "interpreted_as",
+ "searched_at",
+ "results",
+ "total",
+ "available",
+ "sources",
+ "note"
+]search_data18 fields changedInput schema / properties / domainRemoved value: -{
- "maxLength": 100,
- "minLength": 1,
- "type": "string"
-}Input schema / properties / kindAdded value: +{
+ "default": "all",
+ "description": "Search all sources, downloadable datasets, or statistical series",
+ "enum": [
+ "all",
+ "dataset",
+ "statistics"
+ ],
+ "type": "string"
+}Input schema / properties / limit / maximumPrevious value: -50New value: +20Input schema / properties / query / descriptionPrevious value: -"Words in Japanese or English"New value: +"What data to find, preferably in Japanese"Input schema / properties / query / maxLengthPrevious value: -200New value: +80Input schema / properties / query / minLengthPrevious value: -1New value: +2Input schema / properties / sourceIdRemoved value: -{
- "maxLength": 100,
- "minLength": 1,
- "type": "string"
-}Input schema / requiredAdded value: +[
+ "query"
+]Output schema / properties / availableAdded value: +{
+ "additionalProperties": {},
+ "propertyNames": {
+ "type": "string"
+ },
+ "type": "object"
+}Output schema / properties / catalog_versionRemoved value: -{
- "type": "string"
-}Output schema / properties / matchesRemoved value: -{
- "items": {},
- "type": "array"
-}Output schema / properties / noteAdded value: +{
+ "type": "string"
+}Output schema / properties / queryAdded value: +{
+ "type": "string"
+}Output schema / properties / resultsAdded value: +{
+ "items": {},
+ "type": "array"
+}Output schema / properties / searched_atAdded value: +{
+ "type": "string"
+}Output schema / properties / sourcesAdded value: +{
+ "items": {},
+ "type": "array"
+}Output schema / properties / statusAdded value: +{
+ "const": "ok",
+ "type": "string"
+}Output schema / requiredPrevious value: -[
- "matches",
- "total",
- "catalog_version"
-]New value: +[
+ "status",
+ "query",
+ "searched_at",
+ "results",
+ "total",
+ "available",
+ "sources",
+ "note"
+]executesearch_dataverifyRead bounded illicit-economy evidence with provenance, privacy, availability, and federation intact.
Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Tamper-evident daily ledgers of 12 Japanese public-data domains, with cross-ledger entity search.
Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.
Add one secure layer between your agents and this server.
