Self-authenticating booking-request receipt anchored to the Knox chain; never represents a person.
Scored across 3 tools
Each tool targets a distinct action: listing represented agents, anchoring a new booking request, and verifying an existing anchor. There is no overlap in purpose, so an agent can easily select the right tool.
All tool names use snake_case with a clear verb_noun pattern: list_represented_agents, request_booking, verify_booking. The convention is predictable and readable throughout.
Three tools are well-scoped for a booking-request primitive. Each tool earns its place: roster discovery, request anchoring, and verification are the essential operations.
The core lifecycle of listing agents, creating a booking request anchor, and verifying that anchor is covered. Minor gaps remain, such as listing or cancelling existing booking requests, but the stated primitive scope makes these less critical.
Enumerate the Bonis Concierge represented-agent roster. Returns slug, name, charter, bureau, archetype, liveness ('live' = verifiable POST endpoint and Knox event-chain integration today / 'charter' = description filed, integration in progress), and capability-page URL for each agent.
| Name | Required | Description | Default |
|---|---|---|---|
| livenessFilter | No | Optional filter on liveness. Default: 'all'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It does not disclose any behavioral details such as data volume, authentication needs, or rate limits. The read-only nature is implied but not explicitly stated.
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 that efficiently conveys the tool's purpose and output. Every part is necessary, and there is no superfluous 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 tool has only one optional parameter and no output schema. The description covers the return fields and filter semantics adequately. It doesn't address pagination or limits, but the tool is likely returning a small roster, so it's acceptable for a list operation.
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 schema already provides a description for the single parameter (livenessFilter), achieving 100% coverage. The tool description adds value by explaining the meaning of the enum values ('live' and 'charter') in the context of agent status, which helps the agent select the appropriate filter.
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 is used to 'Enumerate the Bonis Concierge represented-agent roster' with a specific verb and resource. It lists the exact fields returned (slug, name, charter, etc.), and the sibling tools are action-oriented (booking), so this read-only listing tool 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 guidance on when to use this tool versus alternatives. There is no mention of use cases, when not to use it, or any prerequisites. The description simply explains what it returns.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Anchor a booking request for a represented Bonis Concierge agent. Returns a booking bundle: Knox anchor record + C2PA-aligned envelope (subset of C2PA 1.4 — adapted for booking events) + FRE 902(13)/(14)-shape representation affidavit. The agency does not adjudicate the merits of any booking, does not guarantee acceptance by the listed agent, does not handle payment under this primitive, and does not represent any natural person. Requires a Knox Bearer API key on the Authorization header — unauthenticated calls are rejected.
| Name | Required | Description | Default |
|---|---|---|---|
| brief | Yes | Description of the booking, in your own words (10–4000 chars). | |
| notes | No | Optional free-form notes (≤ 2000 chars). | |
| startBy | No | Optional ISO-8601 date or date-time when the booking should begin. | |
| agentSlug | Yes | Roster slug of the listed agent (e.g., 'ofac-sdn-screening', 'content-provenance'). Must match the published Bonis Concierge roster — call list_represented_agents to enumerate. | |
| archetype | No | Optional requested presentation archetype if the listed agent supports multiple. | |
| budgetUsdMax | No | Optional maximum USD budget signal. Discovery field — no payment is collected under this primitive. | |
| contactEmail | No | Optional contact email (hashed before anchoring). Provide at least one of contactEmail or contactKnoxKeyId. | |
| contactKnoxKeyId | No | Optional Knox API key ID. Provide at least one of contactEmail or contactKnoxKeyId. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it states the auth requirement (Knox Bearer key, unauthenticated calls rejected), what the tool produces (anchor record + C2PA-aligned envelope + FRE 902(13)/(14)-shape affidavit), and four explicit non-guarantees. It does not disclose idempotency, duplicate handling, or rate limits, which matters for an anchoring/write primitive.
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?
Front-loaded with purpose and return shape, then constraints, then auth. The disclaimer sentence is long but each clause (no adjudication, no acceptance guarantee, no payment, no natural-person representation) carries real decision value for an agent. Slightly dense but no dead weight.
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?
No output schema exists, and the description compensates by naming the three components of the returned bundle, which is genuinely useful. Auth and scope limits are covered. Remaining gaps are failure modes and idempotency/retry behavior for what is effectively an immutable anchoring operation.
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% across all 8 parameters, so the schema already documents brief, agentSlug, archetype enum, budgetUsdMax, and contact fields. The description adds no syntax, format, or constraint detail beyond what the schema provides, so baseline 3 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 gives a specific verb+resource ('Anchor a booking request for a represented Bonis Concierge agent') and enumerates the returned bundle, which clearly separates it from verify_booking. However, it never names a sibling tool, so differentiation is inferable rather than explicit.
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 implied by the verb 'request' and by the scope disclaimers (no payment, no adjudication), but there is no explicit 'use this when X, use verify_booking when Y' guidance. The routing hint to list_represented_agents lives in the schema, not the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify an anchored booking-request record. Given a SHA-256 anchor hash (the payload_hash from a prior request_booking call), return the anchor record, predecessor hash, sequence number, and timestamp. Public — no authentication required. The verification path is also accessible at GET /api/knox/verify?hash=.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes | SHA-256 anchor hash (64 lowercase hex chars). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes public, read-only nature and returned fields. No annotations present; description provides minimal behavioral context but lacks details on limits or error conditions.
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?
Three concise sentences: purpose, usage, and public access. Front-loaded with core action. No fluff.
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?
Simple tool with single parameter; description covers input source, returned fields, public nature, and REST endpoint. Adequate for tool selection and invocation.
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 100%; description adds context by specifying hash is from prior request_booking call and confirms hex format. Exceeds schema-only understanding.
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 verb 'verify' and resource 'anchored booking-request record'. Lists returned fields and input hash source. Differentiates from sibling 'request_booking' and 'list_represented_agents'.
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?
Mentions public access (no auth needed) and REST endpoint alternative. Does not explicitly state when to use versus siblings, though implication is clear.
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.
request_booking1 field changedInput schema / properties / brief / descriptionPrevious value: -"Plain-language description of the booking (10–4000 chars)."New value: +"Description of the booking, in your own words (10–4000 chars)."list_represented_agentsrequest_bookingverify_bookingThe record of what the agent relied on: a signed, chained receipt per cleared read. Verify by id.
Tenant-scoped credentials, training and business records with owner-controlled write approvals.
Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.
Authorize and prove autonomous x402/AP2 agent payments with cryptographic receipts.
Add one secure layer between your agents and this server.