proofrelay.build_audit_pack_manifestBuild a portable hash-only audit pack manifest from bundle, verifier, policy, and evidence hashes without uploading private files or logs.
| Name | Required | Description | Default |
|---|---|---|---|
| audit_pack | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / audit_pack / additionalPropertiesAdded value: +falseInput schema / properties / audit_pack / properties / bundle_hashes / items / patternAdded value: +"^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$"Input schema / properties / audit_pack / properties / evidence_hashes / items / patternAdded value: +"^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$"Input schema / properties / audit_pack / properties / policy_hashes / items / patternAdded value: +"^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$"Input schema / properties / audit_pack / properties / subject_hash / patternAdded value: +"^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$"Input schema / properties / audit_pack / properties / verifier_response_hashes / items / patternAdded value: +"^\\s*(?:sha256:)?[0-9a-fA-F]{64}\\s*$"Input schema / $defsRemoved value: -{
- "AuditPackManifestInput": {
- "description": "Hash-only audit pack manifest input.",
- "properties": {
- "bundle_hashes": {
- "description": "Evidence bundle hashes.",
- "items": {
- "type": "string"
- },
- "title": "Bundle Hashes",
- "type": "array"
- },
- "control_refs": {
- "description": "Public-safe control references.",
- "items": {
- "type": "string"
- },
- "title": "Control Refs",
- "type": "array"
- },
- "evidence_hashes": {
- "description": "Additional evidence artifact hashes.",
- "items": {
- "type": "string"
- },
- "title": "Evidence Hashes",
- "type": "array"
- },
- "generated_at": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Optional ISO-8601 time.",
- "title": "Generated At"
- },
- "pack_id": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Optional audit pack id.",
- "title": "Pack Id"
- },
- "policy_hashes": {
- "description": "Policy or control hashes.",
- "items": {
- "type": "string"
- },
- "title": "Policy Hashes",
- "type": "array"
- },
- "subject_hash": {
- "description": "SHA-256 hash of audit subject.",
- "title": "Subject Hash",
- "type": "string"
- },
- "verifier_response_hashes": {
- "description": "Verifier response hashes.",
- "items": {
- "type": "string"
- },
- "title": "Verifier Response Hashes",
- "type": "array"
- }
- },
- "required": [
- "subject_hash"
- ],
- "title": "AuditPackManifestInput",
- "type": "object"
- }
-}Input schema / properties / audit_pack / $refRemoved value: -"#/$defs/AuditPackManifestInput"Input schema / properties / audit_pack / propertiesAdded value: +{
+ "bundle_hashes": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "control_refs": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "evidence_hashes": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "generated_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "pack_id": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "policy_hashes": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "subject_hash": {
+ "type": "string"
+ },
+ "verifier_response_hashes": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+}Input schema / properties / audit_pack / requiredAdded value: +[
+ "subject_hash"
+]Input schema / properties / audit_pack / typeAdded value: +"object"Input schema / titleRemoved value: -"build_audit_pack_manifestArguments"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the bar is lower. The description still adds real value by promising a 'hash-only' output and explicitly stating that private files and logs are never uploaded — a privacy guarantee not expressible in annotations. It stops short of describing validation failure behavior for malformed hashes.
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?
A single front-loaded sentence with no filler; the artifact being built comes first and the privacy constraint trails. Slightly dense, but every clause carries 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?
The output schema means return values need no prose, and annotations cover the safety profile. However, for a tool whose only parameter is a required nested object with zero field-level documentation, the description leaves the agent guessing about subject_hash, control_refs and hash formatting.
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% on a nested object with seven sub-fields, so the description must compensate. It names four of them indirectly (bundle_hashes, verifier_response_hashes, policy_hashes, evidence_hashes) but says nothing about the required subject_hash, pack_id, control_refs, or generated_at, nor about the sha256 prefix/pattern format expected.
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?
States a specific verb ('Build') and a specific artifact ('portable hash-only audit pack manifest'), and enumerates the hash sources it consumes (bundle, verifier, policy, evidence). It does not, however, distinguish itself from near-siblings like build_closing_proof_pack or build_bundle_draft, which an agent would need to choose among.
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?
Usage is only implied: the agent can infer this assembles a manifest from pre-computed hashes rather than generating them. There is no guidance on when to prefer this over build_closing_proof_pack or build_bundle_draft, and no stated prerequisites such as needing hashes from a prior verify_bundle call.
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.