proofrelay.review_vendor_risk_profileReview public vendor or MCP server risk metadata for governance signals using hashes and declared boundaries only. This is not legal, security, or procurement certification.
| Name | Required | Description | Default |
|---|---|---|---|
| vendor | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / vendor / additionalPropertiesAdded value: +falseInput schema / properties / vendor / properties / prior_incident_hash / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "pattern": "^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / vendor / properties / security_docs_hash / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "pattern": "^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / vendor / properties / subprocessors_hash / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "pattern": "^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / vendor / properties / terms_hash / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "pattern": "^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / vendor / properties / vendor_profile_hash / patternAdded value: +"^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$"Input schema / $defsRemoved value: -{
- "VendorRiskProfileInput": {
- "description": "Public vendor risk profile metadata for review guidance.",
- "properties": {
- "control_refs": {
- "description": "Public-safe control references.",
- "items": {
- "type": "string"
- },
- "title": "Control Refs",
- "type": "array"
- },
- "data_boundary": {
- "default": "unknown",
- "description": "Highest declared data boundary.",
- "enum": [
- "none",
- "metadata",
- "pii",
- "unknown"
- ],
- "title": "Data Boundary",
- "type": "string"
- },
- "prior_incident_hash": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Optional prior-incident disclosure hash.",
- "title": "Prior Incident Hash"
- },
- "requires_authentication": {
- "default": false,
- "description": "Auth is required.",
- "title": "Requires Authentication",
- "type": "boolean"
- },
- "requires_payment": {
- "default": false,
- "description": "Payment is required.",
- "title": "Requires Payment",
- "type": "boolean"
- },
- "security_docs_hash": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Optional security documentation hash.",
- "title": "Security Docs Hash"
- },
- "stores_customer_data": {
- "default": false,
- "description": "Stores customer data.",
- "title": "Stores Customer Data",
- "type": "boolean"
- },
- "subprocessors_hash": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Optional subprocessors disclosure hash.",
- "title": "Subprocessors Hash"
- },
- "terms_hash": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Optional terms hash.",
- "title": "Terms Hash"
- },
- "vendor_name": {
- "description": "Public vendor or MCP server name.",
- "title": "Vendor Name",
- "type": "string"
- },
- "vendor_profile_hash": {
- "description": "SHA-256 vendor profile hash.",
- "title": "Vendor Profile Hash",
- "type": "string"
- }
- },
- "required": [
- "vendor_name",
- "vendor_profile_hash"
- ],
- "title": "VendorRiskProfileInput",
- "type": "object"
- }
-}Input schema / properties / vendor / $refRemoved value: -"#/$defs/VendorRiskProfileInput"Input schema / properties / vendor / propertiesAdded value: +{
+ "control_refs": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "data_boundary": {
+ "enum": [
+ "none",
+ "metadata",
+ "pii",
+ "unknown"
+ ],
+ "type": "string"
+ },
+ "prior_incident_hash": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "requires_authentication": {
+ "type": "boolean"
+ },
+ "requires_payment": {
+ "type": "boolean"
+ },
+ "security_docs_hash": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "stores_customer_data": {
+ "type": "boolean"
+ },
+ "subprocessors_hash": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "terms_hash": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "vendor_name": {
+ "type": "string"
+ },
+ "vendor_profile_hash": {
+ "type": "string"
+ }
+}Input schema / properties / vendor / requiredAdded value: +[
+ "vendor_name",
+ "vendor_profile_hash"
+]Input schema / properties / vendor / typeAdded value: +"object"Input schema / titleRemoved value: -"review_vendor_risk_profileArguments"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds genuine context: evaluation is limited to hashes and declared boundaries, and it explicitly disclaims legal/security/procurement certification, telling the agent not to treat output as authoritative assurance.
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, zero padding, scope constraint front-loaded immediately after the verb. The disclaimer is compact and placed where it reads as a scope limit rather than buried boilerplate.
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?
Output shape is covered by the output schema, and safety behavior is covered by annotations, so the remaining burden is input explanation — which is thin given a nested 10-property vendor object. The definition conveys scope and limits but not enough for an agent to construct a valid vendor payload unaided.
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% across a nested vendor object with ten properties and five sha256-patterned hash fields, so the schema alone leaves meaning implicit. The description partially compensates by gesturing at 'hashes' and 'declared boundaries' (data_boundary), but it never explains the required vendor_name/vendor_profile_hash pairing, hash format expectations, or how control_refs participates.
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+resource: 'Review public vendor or MCP server risk metadata for governance signals', with the scope qualifier 'using hashes and declared boundaries only'. An agent knows what the tool consumes (hashes, declared boundaries) but the description never distinguishes this from the sibling proofrelay.scan_mcp_risk, which sounds like a near-overlapping risk-assessment tool.
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?
'using hashes and declared boundaries only' implies the context of use (metadata-only governance review) and the closing sentence carves out what this is not. But there is no explicit when-to-use statement, no prerequisite, and no named alternative such as scan_mcp_risk for the deeper case — the agent must infer routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.