Skip to main content
Glama

GAIP Witness Agent

by io.github.tjcgraham-rgb
OverviewDiscussionsAdmin

Register what a service should deliver

witness_register_terms

Use this when about to depend on a public HTTPS service and you want neutral evidence of what it delivers. Pass service_url; checks default to HTTP 200 and a non-empty body (also JSON keys, latency, size, regex). Returns a terms_id; then call witness_delivery. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
checksNo1-8 checks, each {"id": "http_status_in", "allowed": [200]}, {"id": "content_type_is", "value": "application/json"}, {"id": "non_empty"}, {"id": "json_parses"}, {"id": "json_required_keys", "keys": ["a.b"]}, {"id": "json_path_equals", "path": "a.b", "value": 1}, {"id": "max_latency_ms", "limit": 2000}, {"id": "max_bytes", "limit": 20000}, {"id": "text_contains", "value": "ok"} or {"id": "regex", "pattern": "ok|up"}.
seller_refNoOptional: name of the supplier. Defaults to the host of service_url.
service_urlYesPublic https URL of the service.
research_consentNoOptional, default false. true lets this record be counted, never named, in GAIP's monthly aggregate research figures (for example for insurers).
data_classificationNoPUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data.PUBLIC

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / research_consent
      Added value: +{
+  "default": false,
+  "description": "Optional, default false. true lets this record be counted, never named, in GAIP's monthly aggregate research figures (for example for insurers).",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / checks / description
      Previous value: -"1-8 checks, each {\"id\": \"http_status_in\", \"allowed\": [200]}, {\"id\": \"content_type_is\", \"value\": \"application/json\"}, {\"id\": \"non_empty\"} or {\"id\": \"json_parses\"}."New value: +"1-8 checks, each {\"id\": \"http_status_in\", \"allowed\": [200]}, {\"id\": \"content_type_is\", \"value\": \"application/json\"}, {\"id\": \"non_empty\"}, {\"id\": \"json_parses\"}, {\"id\": \"json_required_keys\", \"keys\": [\"a.b\"]}, {\"id\": \"json_path_equals\", \"path\": \"a.b\", \"value\": 1}, {\"id\": \"max_latency_ms\", \"limit\": 2000}, {\"id\": \"max_bytes\", \"limit\": 20000}, {\"id\": \"text_contains\", \"value\": \"ok\"} or {\"id\": \"regex\", \"pattern\": \"ok|up\"}."
  3. Changed1 schema field changed
    • changedInput schema / properties / checks / description
      Previous value: -"Checks: http_status_in {allowed}, content_type_is {value}, non_empty, json_parses."New value: +"1-8 checks, each {\"id\": \"http_status_in\", \"allowed\": [200]}, {\"id\": \"content_type_is\", \"value\": \"application/json\"}, {\"id\": \"non_empty\"} or {\"id\": \"json_parses\"}."
  4. Changed5 schema fields changed
    • addedInput schema / properties / checks / description
      Added value: +"Checks: http_status_in {allowed}, content_type_is {value}, non_empty, json_parses."
    • addedInput schema / properties / data_classification / description
      Added value: +"PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data."
    • addedInput schema / properties / seller_ref / description
      Added value: +"Optional: name of the supplier. Defaults to the host of service_url."
    • addedInput schema / properties / service_url / description
      Added value: +"Public https URL of the service."
    • changedInput schema / required
      Previous value: -[
-  "seller_ref",
-  "service_url",
-  "checks"
-]New value: +[
+  "service_url"
+]
  5. Changed4 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "checks": [
+      {
+        "allowed": [
+          200
+        ],
+        "id": "http_status_in"
+      },
+      {
+        "id": "json_parses"
+      }
+    ],
+    "seller_ref": "example-weather-agent",
+    "service_url": "https://weather.example.com/forecast.json"
+  }
+]
    • addedInput schema / properties / data_classification / default
      Added value: +"PUBLIC"
    • addedInput schema / properties / data_classification / type
      Added value: +"string"
    • changedInput schema / required
      Previous value: -[
-  "data_classification",
-  "seller_ref",
-  "service_url",
-  "checks"
-]New value: +[
+  "seller_ref",
+  "service_url",
+  "checks"
+]
  6. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations mark this as a non-read, non-idempotent write with no destruction; the description corroborates and enriches this by disclosing it records only a GAIP receipt, is free, requires public/non-personal inputs, and returns a terms_id (implying a fresh record per call). It doesn't spell out consequences of repeating the call, so it's strong but not exhaustive.

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?

Five short, front-loaded sentences: trigger, required input, defaults, return value/next step, then constraints. Nothing is wasted and the call-relevant facts come first.

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

Completeness5/5

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

With no output schema, the description usefully supplies the return value (terms_id), the workflow it belongs to, and input constraints. For a 5-param, 1-required tool this is sufficient for correct invocation.

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

Parameters4/5

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

Schema coverage is 100% so the baseline is 3, but the description adds genuine value by explaining the default check behavior (HTTP 200 + non-empty body) and enumerating check categories (JSON keys, latency, size, regex) beyond the schema's field list.

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

Purpose5/5

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

States a specific verb+resource ('register what a service should deliver') and frames it as creating neutral evidence of a public service's contract. It also names the downstream sibling (witness_delivery), so an agent can distinguish this registration step from the delivery-verification step without opening a schema.

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

Usage Guidelines4/5

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

Gives a clear trigger ('when about to depend on a public HTTPS service') and the follow-up action ('then call witness_delivery'), plus prerequisites (public, non-personal inputs; free, no account). It lacks an explicit when-not or named alternative, so it falls just short of 5.

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

All GAIP Witness Agent toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources