Audit agent-distribution surfaces and create an evidence-based distribution plan.
Scored across 4 tools
Each tool has a distinct role: start an audit, retrieve audit results, create a distribution plan, and fetch evidence. However, get_audit_result and get_customer_zero_evidence both surface evidence-related data, which could cause some misselection.
All tool names use the same lowercase snake_case verb_noun pattern: audit_app, create_distribution_plan, get_audit_result, get_customer_zero_evidence. The pattern is consistent and predictable.
Four tools cover a focused workflow: start an audit, retrieve its result, create a distribution plan, and fetch customer-zero evidence. This is well-scoped and not bloated.
The core audit-to-plan workflow is supported, but there is no way to retrieve a created distribution plan or manage/cancel audits afterward. Minor gaps, but the main lifecycle is functional.
Queue a bounded audit of a public HTTP or HTTPS app and return an unlisted receipt URL. Reuse get_audit_result until processing completes.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public website or application URL to audit |
| Name | Required | Description |
|---|---|---|
| status | Yes | |
| privacy | Yes | |
| audit_id | Yes | |
| hostname | Yes | |
| receipt_url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate idempotentHint=true and destructiveHint=false; the description adds that the audit is bounded and returns an unlisted receipt URL. No contradictions.
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, no fluff, front-loaded with the key action and outcome. 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?
With an output schema present, the description sufficiently covers the process. Slight lack of detail on audit bounds or prerequisites, but overall 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?
The only parameter 'url' is described in the schema with full coverage. The description adds no additional meaning 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 clearly states the action (queue an audit), resource (public HTTP/HTTPS app), and result (unlisted receipt URL). It distinguishes from sibling tools like get_audit_result and create_distribution_plan.
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 tells when to use the tool and mentions reusing get_audit_result for polling. It does not explicitly state when not to use, but the context of sibling tools makes it clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Turn a completed technical audit into prioritized remediation plus official-registry, public-repository, customer-evidence, and independent-discovery actions.
| Name | Required | Description | Default |
|---|---|---|---|
| audit_id | Yes | Completed audit UUID |
| Name | Required | Description |
|---|---|---|
| plan | Yes | |
| score | Yes | |
| audit_id | Yes | |
| hostname | Yes | |
| limitation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description 'turn into...' suggests state mutation, but annotations declare readOnlyHint=true and destructiveHint=false, creating a contradiction. No clarification is provided.
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 a single sentence with no unnecessary words, effectively conveying the tool's function.
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?
While the description covers the core purpose, the contradiction with annotations and lack of guidance on side effects leaves the tool's behavior unclear.
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 the description adds no additional meaning beyond the schema's parameter description.
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 converts a completed audit into a distribution plan with specific action types, distinguishing it from sibling tools like audit_app, get_audit_result, and get_customer_zero_evidence.
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 use after a completed technical audit but provides no explicit guidance on when to use versus alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the current status, score, findings, privacy state, and evidence URL for an audit UUID.
| Name | Required | Description | Default |
|---|---|---|---|
| audit_id | Yes | Audit UUID returned by audit_app |
| Name | Required | Description |
|---|---|---|
| score | Yes | |
| status | Yes | |
| audit_id | Yes | |
| findings | Yes | |
| hostname | Yes | |
| visibility | Yes | |
| receipt_url | Yes | |
| completed_at | Yes | |
| requested_at | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing safe, idempotent read behavior. The description adds value by listing the specific fields returned (status, score, etc.), which is not detailed in annotations. However, it does not describe pagination, error cases, or latency, but given the annotations, the bar is lower and the added context is sufficient.
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 a single, well-structured sentence with no wasted words. It front-loads the action ('Retrieve') and resource, then lists the specific fields. Every word contributes to clarity.
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 tool's simplicity (single parameter, idempotent read), an output schema exists, so the description need not detail return format. It covers all key fields returned. Minor omission: no statement about what happens if the audit UUID does not exist, but for a retrieval tool with idempotentHint, this is acceptable.
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% for the single parameter audit_id, with a schema description stating 'Audit UUID returned by audit_app'. The tool description merely reiterates 'for an audit UUID', adding minimal new meaning. Baseline 3 is appropriate since the schema already explains the parameter adequately.
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 ('Retrieve') and clearly identifies the resource ('audit result for an audit UUID'). It lists the exact data fields returned (status, score, findings, privacy state, evidence URL), leaving no ambiguity. Sibling tools like audit_app (initiates audit) and create_distribution_plan are distinct, so the purpose is well differentiated.
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 guidance on when to use this tool versus alternatives. For example, it does not mention that it should be called after a successful audit_app invocation or suggest conditions for using get_customer_zero_evidence instead. The agent must infer usage from context signals.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the public self-audit evidence and the explicit boundary between technical readiness and independent discovery.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| claim | Yes | |
| next_proof | Yes | |
| receipt_url | Yes | |
| customer_zero | Yes | |
| externally_verified | Yes | |
| technical_audit_score | Yes | |
| independent_discovery_status | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and idempotent behavior. The description adds that the evidence is 'public self-audit' and relates to a boundary, which provides some additional context beyond annotations but is not extensive.
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 a single, non-redundant sentence that gets straight to the point. No waste or extraneous information.
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 parameters and presence of an output schema, the description explains the return content adequately for a simple retrieval tool. However, it could clarify what 'explicit boundary' means or note if results are fixed.
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 are no parameters, so schema coverage is trivially 100%. The description does not need to add parameter info. Baseline 4 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 clearly states the tool returns 'public self-audit evidence' and an 'explicit boundary', which is a specific resource. However, it does not explicitly differentiate from sibling tools like get_audit_result, which may overlap.
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 (e.g., audit_app, get_audit_result) is provided. The description implies context but offers no explicit usage criteria or exclusions.
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.
audit_app1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "audit_id": {
+ "format": "uuid",
+ "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+ "type": "string"
+ },
+ "hostname": {
+ "type": "string"
+ },
+ "privacy": {
+ "const": "unlisted-noindex-unless-explicitly-published",
+ "type": "string"
+ },
+ "receipt_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "status": {
+ "const": "queued",
+ "type": "string"
+ }
+ },
+ "required": [
+ "audit_id",
+ "status",
+ "hostname",
+ "receipt_url",
+ "privacy"
+ ],
+ "type": "object"
+}create_distribution_plan1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "audit_id": {
+ "format": "uuid",
+ "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+ "type": "string"
+ },
+ "hostname": {
+ "type": "string"
+ },
+ "limitation": {
+ "type": "string"
+ },
+ "plan": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "action": {
+ "type": "string"
+ },
+ "channel": {
+ "type": "string"
+ },
+ "priority": {
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "reason": {
+ "type": "string"
+ },
+ "status": {
+ "enum": [
+ "required",
+ "recommended",
+ "verified",
+ "not-applicable"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "priority",
+ "status",
+ "channel",
+ "action",
+ "reason"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "score": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "required": [
+ "audit_id",
+ "hostname",
+ "score",
+ "plan",
+ "limitation"
+ ],
+ "type": "object"
+}get_audit_result1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "audit_id": {
+ "format": "uuid",
+ "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+ "type": "string"
+ },
+ "completed_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "findings": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "evidence": {
+ "type": "string"
+ },
+ "id": {
+ "type": "string"
+ },
+ "label": {
+ "type": "string"
+ },
+ "maxPoints": {
+ "type": "number"
+ },
+ "points": {
+ "type": "number"
+ },
+ "status": {
+ "enum": [
+ "pass",
+ "warn",
+ "fail",
+ "not-applicable"
+ ],
+ "type": "string"
+ },
+ "url": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "required": [
+ "id",
+ "label",
+ "status",
+ "points",
+ "maxPoints",
+ "evidence",
+ "url"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "hostname": {
+ "type": "string"
+ },
+ "receipt_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "requested_at": {
+ "type": "string"
+ },
+ "score": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "status": {
+ "enum": [
+ "queued",
+ "running",
+ "completed",
+ "failed"
+ ],
+ "type": "string"
+ },
+ "visibility": {
+ "enum": [
+ "public",
+ "unlisted-noindex"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "audit_id",
+ "status",
+ "score",
+ "hostname",
+ "findings",
+ "receipt_url",
+ "visibility",
+ "requested_at",
+ "completed_at"
+ ],
+ "type": "object"
+}get_customer_zero_evidence1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "claim": {
+ "type": "string"
+ },
+ "customer_zero": {
+ "const": true,
+ "type": "boolean"
+ },
+ "externally_verified": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "identifier": {
+ "type": "string"
+ },
+ "type": {
+ "type": "string"
+ },
+ "url": {
+ "format": "uri",
+ "type": "string"
+ }
+ },
+ "required": [
+ "type",
+ "identifier",
+ "url"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "independent_discovery_status": {
+ "const": "not-yet-proven",
+ "type": "string"
+ },
+ "next_proof": {
+ "type": "string"
+ },
+ "receipt_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "technical_audit_score": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "required": [
+ "customer_zero",
+ "technical_audit_score",
+ "receipt_url",
+ "claim",
+ "externally_verified",
+ "independent_discovery_status",
+ "next_proof"
+ ],
+ "type": "object"
+}audit_appcreate_distribution_planget_audit_resultget_customer_zero_evidenceAgent-run distribution: find private communities, estimate CPA, launch admin-approved campaigns.
Audit lead-delivery workflows, find reliability gaps, and generate a LeadProof integration plan.
Read-only agent-commerce audit for UCP, x402, remediation and verification evidence.
Sourced software, security and AI evidence, plus scoped requests for specialist agent help.
Add one secure layer between your agents and this server.