GAIP — evidence on AI agents before and after you call them

Verify a delivery or citations

gaip_verify

Use this when asked whether a service delivered what was promised or whether cited pages contain the quoted text. Pass citations, or a service url (+ checks, the result you got), or claims with observations. Returns a result per item and a receipt. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Claims: the agent or supplier they are about. Delivery: the public https service URL that should deliver.
`checks`	No	Optional (delivery): what a good response is, e.g. [{"id": "http_status_in", "allowed": [200]}, {"id": "json_parses"}]. Default: HTTP 200 and a non-empty body.
`claims`	No	Claims to record about `url`: each a sentence or {id, text}. Each is compared with the `observations` you supply; without them it stays UNTESTED.
`result`	No	Optional (delivery): the response you received. Omitted: GAIP fetches the service URL now (public replay).
`verbose`	No	Optional: true returns the full result with every underlying field. Default: a short answer.
`metadata`	No	Optional (claims): the published agent card, MCP or OpenAPI document.
`terms_id`	No	Optional (delivery): terms_id from an earlier registration, instead of url.
`citations`	No	Citations to check: each {url, quote?} or just a URL. GAIP fetches each page once (robots.txt respected) and looks for the quote.
`observations`	No	Optional (claims): what you saw, each {claim_id, result: PASS\|FAIL, detail}.
`continuity_handle`	No	Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones (needed to see or remove your watches later).

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 1, 2026

changedInput schema / properties / checks / examples

Previous value: -[
-  [
-    {
-      "allowed": [
-        200
-      ],
-      "id": "http_status_in"
-    },
-    {
-      "id": "content_type_is",
-      "value": "application/json"
-    },
-    {
-      "id": "non_empty"
-    },
-    {
-      "id": "json_parses"
-    }
-  ]
-]New value: +[
+  [
+    {
+      "allowed": [
+        200
+      ],
+      "id": "http_status_in"
+    },
+    {
+      "id": "content_type_is",
+      "value": "application/json"
+    },
+    {
+      "id": "non_empty"
+    },
+    {
+      "id": "json_parses"
+    }
+  ],
+  [
+    {
+      "allowed": [
+        200
+      ],
+      "id": "http_status_in"
+    },
+    {
+      "id": "json_required_keys",
+      "keys": [
+        "status"
+      ]
+    },
+    {
+      "id": "json_path_equals",
+      "path": "status",
+      "value": "ok"
+    },
+    {
+      "id": "max_latency_ms",
+      "limit": 2000
+    }
+  ]
+]

changedInput schema / properties / checks / items / properties / id / description

Previous value: -"http_status_in (needs allowed), content_type_is (needs value), non_empty, json_parses."New value: +"http_status_in (allowed), content_type_is (value), non_empty, json_parses, json_required_keys (keys), json_path_equals (path, value), max_latency_ms (limit), max_bytes (limit), text_contains (value), regex (pattern)."

changedInput schema / properties / checks / items / properties / id / enum

Previous value: -[
-  "http_status_in",
-  "content_type_is",
-  "non_empty",
-  "json_parses"
-]New value: +[
+  "http_status_in",
+  "content_type_is",
+  "non_empty",
+  "json_parses",
+  "json_required_keys",
+  "json_path_equals",
+  "max_latency_ms",
+  "max_bytes",
+  "text_contains",
+  "regex"
+]

addedInput schema / properties / checks / items / properties / keys

Added value: +{
+  "description": "json_required_keys: top-level or dotted keys that must exist, e.g. [\"a.b\"].",
+  "items": {
+    "maxLength": 200,
+    "type": "string"
+  },
+  "maxItems": 20,
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / properties / checks / items / properties / limit

Added value: +{
+  "description": "max_latency_ms: milliseconds (1-60000); max_bytes: body bytes (1-32768).",
+  "maximum": 60000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / checks / items / properties / path

Added value: +{
+  "description": "json_path_equals: dotted path, list items by index, e.g. items.0.id.",
+  "maxLength": 200,
+  "type": "string"
+}

addedInput schema / properties / checks / items / properties / pattern

Added value: +{
+  "description": "regex: bounded pattern searched in the body; no nested quantifiers.",
+  "maxLength": 200,
+  "type": "string"
+}

changedInput schema / properties / checks / items / properties / value / description

Previous value: -"content_type_is: the expected media type, e.g. application/json."New value: +"content_type_is: media type, e.g. application/json; text_contains: case-sensitive text; json_path_equals: the expected value (GAIP also accepts a number, boolean, null, array or object)."

changedInput schema / properties / checks / items / properties / value / maxLength
```
Previous value: -100New value: +200
```

Changed9 schema fields changedSep 30, 2026

changedInput schema / properties / checks / description

Previous value: -"Optional (delivery): what a good response is: http_status_in {allowed}, content_type_is {value}, non_empty, json_parses. Default: HTTP 200, non-empty."New value: +"Optional (delivery): what a good response is, e.g. [{\"id\": \"http_status_in\", \"allowed\": [200]}, {\"id\": \"json_parses\"}]. Default: HTTP 200 and a non-empty body."

addedInput schema / properties / checks / examples

Added value: +[
+  [
+    {
+      "allowed": [
+        200
+      ],
+      "id": "http_status_in"
+    },
+    {
+      "id": "content_type_is",
+      "value": "application/json"
+    },
+    {
+      "id": "non_empty"
+    },
+    {
+      "id": "json_parses"
+    }
+  ]
+]

addedInput schema / properties / checks / items / additionalProperties
```
Added value: +false
```

addedInput schema / properties / checks / items / properties

Added value: +{
+  "allowed": {
+    "description": "http_status_in: the acceptable HTTP statuses, e.g. [200].",
+    "items": {
+      "maximum": 599,
+      "minimum": 100,
+      "type": "integer"
+    },
+    "maxItems": 10,
+    "minItems": 1,
+    "type": "array"
+  },
+  "id": {
+    "description": "http_status_in (needs allowed), content_type_is (needs value), non_empty, json_parses.",
+    "enum": [
+      "http_status_in",
+      "content_type_is",
+      "non_empty",
+      "json_parses"
+    ],
+    "type": "string"
+  },
+  "value": {
+    "description": "content_type_is: the expected media type, e.g. application/json.",
+    "maxLength": 100,
+    "type": "string"
+  }
+}

addedInput schema / properties / checks / items / required
```
Added value: +[
+  "id"
+]
```
changedInput schema / properties / checks / maxItems
```
Previous value: -10New value: +8
```
addedInput schema / properties / checks / minItems
```
Added value: +1
```

changedInput schema / properties / claims / description

Previous value: -"Claims to compare with observations: each a sentence or {id, text}."New value: +"Claims to record about `url`: each a sentence or {id, text}. Each is compared with the `observations` you supply; without them it stays UNTESTED."

addedInput schema / properties / verbose

Added value: +{
+  "default": false,
+  "description": "Optional: true returns the full result with every underlying field. Default: a short answer.",
+  "type": "boolean"
+}

AddedSep 28, 2026

TDQS

A4.1/5.0

Behavior5/5

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

With annotations already covering the safety profile, the description adds substantial context beyond them: no account required, it records a GAIP receipt, inputs must be public and non-personal, GAIP fetches each cited page once with robots.txt respected, and it will fetch the service URL itself if result is omitted. These are exactly the side-effect and constraint details an agent needs.

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

Conciseness4/5

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

Front-loaded with the usage trigger, then the input combinations, then the return shape and constraints. Every sentence carries information, though the four-sentence block is dense and slightly overloaded for a single paragraph.

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

Completeness4/5

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

For a complex 10-parameter tool with nested objects and no output schema, the description covers the three invocation modes, the return shape ('a result per item and a receipt') and the key constraints. It is close to complete, with only minor gaps around failure modes and the meaning of PASS/FAIL receipts.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all ten parameters in depth, including the checks enum and defaults. The description restates the three input combinations but adds no syntax or format detail beyond the schema, so the baseline of 3 applies.

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 the specific task clearly: verifying whether a service delivered what was promised, or whether cited pages contain quoted text. That is a concrete verb+resource pairing an agent can act on. It does not, however, differentiate itself from the sibling tools gaip_check, gaip_diagnose or gaip_watch, so the agent must infer the boundary.

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?

It gives an explicit trigger ('Use this when asked whether...') and enumerates the three valid invocation shapes (citations; url + checks + result; claims + observations), which is real routing guidance. It stops short of naming when NOT to use it or pointing to a sibling alternative, so it is clear context without exclusions.

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

All GAIP — evidence on AI agents before and after you call them tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Verify a delivery or citations

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources