Decode an SSTV audio recording and anchor its fingerprint and image hash to the Knox event chain.
Scored across 2 tools
The two tools have clearly distinct purposes: one performs a decode-and-anchor operation, the other verifies a previously anchored record. There is no overlap or ambiguity between them.
Both tool names follow a consistent verb_noun pattern (decode_sstv, verify_sstv_decode), though the second inverts the object slightly (sstv_decode vs decode_sstv). Minor deviation but still predictable.
Two tools is on the thin side for a server, but the narrow scope (decode and verify SSTV audio) justifies the minimal surface. It is borderline but not unreasonable.
The core decode and verify lifecycle is covered, but there is no way to list or search anchored records, and the decode tool only supports one SSTV mode (Martin M1). Minor gaps exist but the primary workflow is functional.
Demodulate a presented slow-scan-television (SSTV) audio recording, anchor the audio fingerprint and the decoded image hash to the Knox event chain, and return a receipt bundle (Knox anchor + C2PA-aligned envelope + FRE 902(13)/(14)-shape affidavit). Audio bytes are NOT retained — only the SHA-256 fingerprint and the decoded image are anchored. Bonis Systems does not capture audio on its own; the audio must be presented by the caller (a public WebSDR recording, a customer-controlled SDR capture they consent to submit, or audio they own). Phase 1 supports Martin M1 (VIS code 0x2C, 320×256 RGB). Other VIS codes return mode = 'unsupported' with detected hex. Requires a Knox Bearer API key on the Authorization header — unauthenticated calls are rejected.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Display name for the recording (max 256 chars). | |
| capture | No | Optional capture-context metadata. | |
| sampleRate | No | Required when audioFormat = 'pcm16-mono'. | |
| audioBase64 | Yes | Base64-encoded audio. Either a complete WAV file (RIFF/WAVE, 8/16/24-bit PCM or 32-bit IEEE float, mono or stereo, 4-192 kHz) or raw 16-bit signed little-endian mono PCM samples. | |
| audioFormat | No | Audio container ('wav' default, or 'pcm16-mono'). |
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 discloses that audio bytes are NOT retained, that only SHA-256 fingerprint and decoded image are anchored, that only Martin M1 (VIS 0x2C) is supported, unsupported modes return mode='unsupported' with detected hex, and unauthenticated calls are rejected. These are meaningful behavioral traits beyond the schema.
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 multi-sentence but each sentence adds value: core action, privacy note, source requirements, supported format, and auth requirement. It is front-loaded with the primary verb and resource. Slightly longer than minimal but not wasteful.
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, so the description appropriately explains the return receipt bundle (Knox anchor, C2PA envelope, affidavit) and the unsupported-mode response (mode='unsupported' with hex). It also covers auth and input constraints. For a tool with nested objects and 5 parameters, it is fairly complete; missing details like error codes are minor.
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 input schema covers all parameters with descriptions (100% coverage), so the baseline is 3. The description adds general context about the workflow (e.g., audio not retained) but does not add per-parameter semantics beyond what the schema already provides. It neither compensates nor detracts.
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 begins with a precise action: 'Demodulate a presented slow-scan-television (SSTV) audio recording' and enumerates the output bundle (Knox anchor, C2PA envelope, affidavit). It clearly distinguishes from the sibling verify_sstv_decode by the verb 'decode' vs 'verify', making the tool's role unambiguous.
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 that audio must be presented by the caller (WebSDR, customer-controlled capture, or owned audio) and that a Knox Bearer API key is required. It does not explicitly say 'use verify_sstv_decode for verification', but the context implies this tool is for decoding, which is sufficient for a competent agent. Missing explicit exclusions but not misleading.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify a previously anchored SSTV-decode record. Given a SHA-256 anchor hash (the payload_hash from a prior decode_sstv call), return the anchor record, predecessor hash, sequence number, and timestamp. Public — no authentication required. The verification path itself 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?
With no annotations provided, the description sufficiently discloses that the tool is public, returns specific fields (anchor record, predecessor hash, etc.), and mentions an alternative API endpoint. No contradictions with missing 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 concise sentences, each providing distinct information: action, return fields, and public access with endpoint. No redundant 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?
For a simple single-parameter tool with no output schema, the description is thorough in covering purpose, input, output details, and usage context. Minor missing error handling info, but overall complete.
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%, so baseline is 3. The description adds value by linking the 'hash' parameter to the output of 'decode_sstv' and specifying it is SHA-256, beyond the schema pattern.
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 ('verify') and the resource ('previously anchored SSTV-decode record'), and distinguishes it from the sibling 'decode_sstv' by referencing the hash from a prior decode call.
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 explicitly indicates when to use this tool (after a 'decode_sstv' call) and states it is public. It does not explicitly exclude scenarios, but the context 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.
decode_sstvverify_sstv_decodeAnchor a content-creation event to the Knox chain; returns a C2PA-aligned, FRE 902-shaped bundle.
Stamp any data to the Markovian chain for a verifiable provenance receipt. Proves timing, not truth.
Verify VerixID proof-of-existence records and optionally prove ownership.
Remote MCP for C2PA intake verifier MCP, structured receipts, audit logs, and reviewer-ready evidenc
Add one secure layer between your agents and this server.