Verify an artifact an AI agent produced — schema, emptiness, provenance and mandate authority — before you accept the work or pay for it. Ed25519-signed and verifiable without this service; 20 checks a day free, then 0.005 USDC per call over x402.
Scored across 2 tools
The two tools differ only along a clear single-vs-batch axis, and each description explicitly states when to use it (one artifact vs. a batch like a scan report or finding list). An agent can unambiguously pick the right one based on input cardinality.
Both names use the same snake_case verb_noun stem, with the batch variant formed by a predictable '_batch' suffix. This is a textbook, fully consistent pattern for a two-tool pair.
Two tools is on the thin side for an 'attestation' server; the surface reduces to one operation with a batch variant. It is well-scoped and nothing is redundant, but the server feels like a single capability rather than a complete toolset.
Verification is covered thoroughly (single and batch), but the surrounding lifecycle described in the descriptions — issuing/registering signed mandates and provenance records, revoking them, or retrieving past verdicts — has no corresponding tools. Agents can verify but cannot provision the inputs verification depends on, which is a notable gap.
Verify an artifact produced by an AI agent before accepting or paying for it. Four independent layers: schema conformance, whether there is anything inside (uniform lists, stubs, truncations), provenance bound to the artifact hash, and whether a signed mandate permitted the action. Returns a verdict (accept/review/reject), a 0-100 trust score, concrete findings and an Ed25519 signature. Rule-based, no LLM: the same artifact always yields the same result. Use before accepting work from another agent and before payment.
| Name | Required | Description | Default |
|---|---|---|---|
| schema | No | Optional JSON Schema the artifact must satisfy. | |
| source | No | Where the artifact came from, recorded in the attestation. | |
| artifact | Yes | The agent artifact: object, array or string. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnly, idempotent, closed-world), it discloses that verification is rule-based with no LLM and fully deterministic ("the same artifact always yields the same result"), which tells the agent the result is reproducible and cacheable. It also names the non-obvious provenance/mandate checks that the caller cannot infer from the name.
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 purpose and the payoff (before accepting/paying) are front-loaded in the first sentence, and the four layers are compactly enumerated. Every sentence carries information the agent needs; nothing is padding.
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?
There is no output schema, but the description compensates by naming the return shape: verdict (accept/review/reject), 0-100 trust score, findings, and an Ed25519 signature. Combined with the safety annotations, this is sufficient for an agent to call the tool and interpret its result.
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%, so the baseline is 3. The prose adds no per-parameter meaning (it never explains how `schema` is applied or that `source` is only recorded in the attestation) beyond stating the four verification layers, so the schema remains the sole source for parameter semantics.
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 gives a precise verb+resource (verify an artifact produced by an AI agent) and enumerates the four checks performed (schema conformance, emptiness, provenance bound to hash, signed mandate), so the agent knows exactly what the tool inspects. It does not differentiate from the sibling bridge_check, which is the only missing element for 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?
It states clear usage context: "Use before accepting work from another agent and before payment." That is an explicit trigger condition rather than an implied one. It offers no when-not guidance and does not mention the alternative sibling bridge_check, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify several artifacts at once — a scan report, a list of findings, a set of tool descriptions. One call, one verdict per artifact, plus a summary of how many were accepted, need review, or were rejected. Use when an agent produced a batch (twenty findings from a security scan, for example) and each of them has to be checked before the work is paid for.
| Name | Required | Description | Default |
|---|---|---|---|
| schema | No | Optional JSON Schema every artifact must satisfy. | |
| source | No | Where the artifacts came from, recorded in the attestations. | |
| artifacts | Yes | The artifacts to verify: objects, arrays or strings. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds useful behavioral context by describing the per-artifact verdict and batch summary counts, though it does not explain verdict criteria or batch limits.
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, front-loaded with the batch action and result format, then a concrete usage condition. There is no wasted text.
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 annotations covering safety and schema covering all parameters, the description supplies the missing return behavior at a high level. It remains slightly incomplete on verdict structure, batch size limits, and how schema failures are reported.
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%, so the schema already documents artifacts, optional schema, and source. The description gives examples of artifact types but adds no parameter-specific syntax or constraints beyond the schema.
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 names a specific verb and resource ('verify several artifacts at once') and clarifies batch scope versus the singular sibling verify_artifact. It also specifies the output shape: one verdict per artifact plus an acceptance/review/rejection summary.
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?
It gives a clear triggering condition: use when an agent has produced a batch of artifacts that each need checking before payment. It does not explicitly say when not to use it or directly name verify_artifact for single-item cases, so it falls short of full alternative routing.
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.
bridge_checkverify_artifact_batchbridge_checkverify_artifact
Add one secure layer between your agents and this server.