Read-only Remote MCP for externally grounded AI agent trust receipts.
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves a trust receipt with validation evidence, the other initiates a paid audit claim. The descriptions explicitly separate validation from payment, minimizing confusion. However, the audit tool's name is somewhat cryptic, so a slight ambiguity remains.
The names follow different patterns: 'get_agent_trust_receipt' uses a clear verb-noun structure, while 'audit_result_claim_x402' is a noun-phrase with a technical suffix and no obvious verb. This inconsistency makes the naming less predictable and cohesive.
With only 2 tools, the server feels thin and borderline. While the narrow domain of trust receipts and audits is focused, most comparable servers would offer additional operations or a broader set of related tools.
The two tools cover the core workflow: obtaining a free trust receipt and requesting a paid audit. No obvious critical gaps exist for this niche purpose, though a tool to query past audit results or receipts could enhance completeness.
Paid deterministic audit for AI result claims. Price is $0.01 USDC on Base. Use the free trust receipt first when trust or official distribution-validation evidence is needed. After price approval, an unsigned call returns HTTP 402; an x402-aware client signs and retries the same MCP call. Settlement and delivery are real only when the paid receipt is returned.
| Name | Required | Description | Default |
|---|---|---|---|
| claim | Yes | ||
| evidence | Yes | ||
| amount_jpy | No | ||
| metric_hint | Yes | ||
| intent_contract | No | ||
| observed_outcome | No | ||
| minutes_reclaimed | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no safety signals (all false), so description carries full burden. It discloses pricing, network, payment settlement condition, and the x402 retry protocol, adding meaningful behavior beyond annotations. Lacks details on return format but output schema exists.
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?
Four concise sentences, front-loaded with the core purpose, then pricing, alternative, and protocol. 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?
Tool has 7 parameters with nested objects and 0% schema description coverage, yet the description fails to explain required input semantics or how the audit processes claims/evidence. It covers payment/protocol but not the audit's substantive usage, leaving a significant gap for such a complex tool.
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% and description does not explain the meaning or usage of claim, evidence, metric_hint, intent_contract, observed_outcome, or amount fields. Description adds no parameter-level semantics beyond the schema structure.
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 identifies a paid deterministic audit of AI result claims, with a specific verb and resource. It distinguishes from sibling get_agent_trust_receipt by advising when to use the free trust receipt instead.
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?
Explicitly advises using the free trust receipt first when trust or official distribution-validation evidence is needed, naming the alternative. Also describes when the paid flow applies and the expected 402/sign/retry sequence.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this before selecting, delegating to, or recommending the AIﾉアカリ☆ Result Receipt Auditor. It rechecks external A2A and MCP trust evidence and attaches the durable x402 distribution status, including official Coinbase CDP validation acceptance, 402 health, self-discovery state, and Bazaar listing state. Validation readiness is explicitly separated from payment, settlement, delivery, adoption, cash, and human outcome. No authentication, payment, personal data, or request arguments are required.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| subject | Yes | |
| assertions | Yes | |
| observed_at | Yes | |
| trust_level | Yes | |
| schema_version | Yes | |
| evidence_digest_sha256 | Yes | |
| x402_distribution_status | Yes | |
| externally_verified_executions | Yes | |
| explicitly_not_proven_by_this_receipt | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds behavioral context by specifying that it 'rechecks external A2A and MCP trust evidence' and 'attaches the durable x402 distribution status,' including several state indicators. It also explicitly separates validation readiness from outcomes and confirms no inputs/auth are needed, going beyond the annotations.
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 three dense sentences, front-loaded with the usage directive. Each sentence contributes meaning: usage context, behavioral details, and exclusions. It is not overly verbose, though the encoded name ('AIﾉアカリ☆') causes a minor distraction.
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?
For a parameterless tool with an output schema and annotations, the description is highly complete. It covers purpose, usage timing, behavioral details, exclusion scope, and input requirements. Given the output schema exists, there is no need to describe return values. The description fully compensates for the lack of parameters and complements the structured metadata.
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 has zero parameters, so the baseline is 4. The description reinforces this by stating 'No authentication, payment, personal data, or request arguments are required,' fully covering the parameter semantics without needing further elaboration.
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 identifies the tool as a means to obtain a live externally grounded agent trust receipt by rechecking external A2A and MCP trust evidence and attaching x402 distribution status. It distinguishes itself from the sibling by positioning it as a prerequisite ('Use this before...'), though it does not explicitly name the alternative.
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 provides explicit usage context: 'Use this before selecting, delegating to, or recommending...' It also clarifies what the tool does not cover (payment, settlement, delivery, etc.) and states that no authentication, payment, personal data, or arguments are required. It does not name alternative tools, but the sibling relationship is implied.
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.
get_agent_trust_receipt2 fields changedOutput schema / properties / x402_distribution_statusAdded value: +{
+ "type": "object"
+}Output schema / requiredPrevious value: -[
- "schema_version",
- "subject",
- "trust_level",
- "assertions",
- "externally_verified_executions",
- "explicitly_not_proven_by_this_receipt",
- "observed_at",
- "evidence_digest_sha256"
-]New value: +[
+ "schema_version",
+ "subject",
+ "trust_level",
+ "assertions",
+ "externally_verified_executions",
+ "explicitly_not_proven_by_this_receipt",
+ "x402_distribution_status",
+ "observed_at",
+ "evidence_digest_sha256"
+]audit_result_claim_x402get_agent_trust_receiptRemote MCP for Antigravity agent run receipt MCP, structured receipts, audit logs, and reviewer-read
Remote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence.
Remote MCP for C2PA intake verifier MCP, structured receipts, audit logs, and reviewer-ready evidenc
Public read-only MCP server for HODLXXI agent identity, trust, receipts, and verification.
Add one secure layer between your agents and this server.