Skip to main content
Glama

AIDNode | AI Agent Support Network

witness

AIDNode Witness v2: validate supplied structured evidence and issue HMAC-signed, hash-based validation receipt; not real-world action attestation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operation_id": "<operation_id>",
      "document": "<document>",
      "required_fields": "<required_fields>"
    },
    "name": "witness"
  }
}

Input Schema

NameRequiredDescriptionDefault
documentYes
field_rulesNo
operation_idYesUnique call id 8-100 characters; counted once by beta ledger
expected_typesNo
expected_sha256No
expected_valuesNo
required_fieldsYes
external_evidenceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / field_rules
      Added value: +{
      +  "additionalProperties": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "enum": {
      +        "maxItems": 100,
      +        "minItems": 1,
      +        "type": "array"
      +      },
      +      "format": {
      +        "enum": [
      +          "uuid",
      +          "sha256",
      +          "date-time"
      +        ],
      +        "type": "string"
      +      },
      +      "max_length": {
      +        "maximum": 100000,
      +        "minimum": 0,
      +        "type": "integer"
      +      },
      +      "maximum": {
      +        "type": "number"
      +      },
      +      "min_length": {
      +        "maximum": 100000,
      +        "minimum": 0,
      +        "type": "integer"
      +      },
      +      "minimum": {
      +        "type": "number"
      +      },
      +      "non_empty": {
      +        "type": "boolean"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose two meaningful traits: the tool issues an HMAC-signed, hash-based receipt (a write/side-effect) and it does not attest real-world actions. Missing are whether receipts are persisted, what authorization or signing key is needed, and any idempotency or failure behavior for a tool whose schema includes a 'operation_id' described as being counted once by a ledger.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence that establishes identity, core action, and boundary in minimal space, with zero filler. Nothing in it is redundant with the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with nested rule objects, no output schema, and no annotations, a single sentence is not enough: an agent cannot tell how a validation receipt is returned, whether validation failure is an error or a result, or what the field_rules and external_evidence inputs are for. It establishes the concept but leaves the call mechanics undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 13% across 8 parameters, with nested objects like field_rules and external_evidence, so the description is obligated to compensate and does not. Terms like 'structured evidence' and 'hash-based' loosely gesture at expected_sha256 and document, but document, required_fields, expected_types, expected_values, field_rules, and external_evidence carry no explanatory meaning from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource pair — 'validate supplied structured evidence' — and adds a product/version tag plus an explicit scope negation ('not real-world action attestation'). It is far more specific than the bare tool name 'witness', though it never contrasts itself with the similar-sounding sibling 'verify', which an agent would likely confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The negative scoping clause tells the agent when NOT to use it (real-world action attestation), which is genuine guidance. But there is no positive statement of the situation that selects this tool over 'verify', 'monitor', or 'repair', so the when-to-use half of the decision is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.