Skip to main content
Glama

ZEAM :: Prism

by com.zeamprism
OverviewDiscussionsAdmin

Compare two contract snapshots

attest_drift
Read-onlyIdempotent

Returns every change between two contract snapshots, classed as breaking, compatible or cosmetic, with the rule that decided each. Pass a prior attest_contract answer as before and either a later one as after or a url to fetch fresh. Both hashes are computed from the snapshot content; a hash supplied with a snapshot is checked against it and a mismatch is reported, never trusted. Nothing is stored between calls: the caller holds the history. With both snapshots it makes no request and finishes in milliseconds; with url it makes the three requests attest_contract makes, each waited on for up to 15 s and reported timed_out, never as the server's answer, when not answered by then; a call cut for time returns nothing. Paid, on a line: $0.000001 per millisecond. With no wallet code, ZEAM :: Pass buys the time and opens the line: a pass (https://mcp.zeamprism.com/pass) or your own wallet (https://mcp.zeamprism.com/how-to-pay). Example: {"url":"https://mcp.zeamprism.com/mcp","before":{"snapshot":[]}}

Input Schema

NameRequiredDescriptionDefault
urlNooptional string — fetch a fresh contract from this MCP endpoint as `after`.
lineNoOptional. A line credential, for a client that cannot send the x-line header or _meta["zeam-pass/line"]: the call runs on that line's time.
afterNooptional object — a later `contract` answer; omit to fetch from `url`.
beforeYesobject — a prior `contract` answer from this shelf (or its `snapshot` array). Its `hash` field is recomputed from the snapshot, not trusted.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / anyOf
      Previous value: -[
-  {
-    "properties": {
-      "after": {
-        "anyOf": [
-          {
-            "description": "hash computed from the content of `after`",
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "at": {
-        "anyOf": [
-          {
-            "description": "ISO time of the run",
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "before": {
-        "anyOf": [
-          {
-            "description": "hash computed from the content of `before`",
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "breaking": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "changes": {
-        "anyOf": [
-          {
-            "items": {},
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "compatible": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "cosmetic": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "error": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "evidence": {
-        "anyOf": [
-          {
-            "description": "every request made, in the order sent: method, url, request headers of note, status, ms; a request that drew no answer has status 0 and its error, a redirect followed is listed in redirects, and a request still unanswered when a report was cut has unanswered: true",
-            "items": {},
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "hash_check": {
-        "anyOf": [
-          {
-            "description": "for each snapshot that came with a hash: supplied, computed, matches",
-            "items": {},
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "ok": {
-        "anyOf": [
-          {
-            "type": "boolean"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "rules": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "same": {
-        "anyOf": [
-          {
-            "description": "true when the two hashes computed here from the snapshot content are equal",
-            "type": "boolean"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "unclassified": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "url": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "type": "object"
-  },
-  {
-    "required": [
-      "error"
-    ],
-    "type": "object"
-  },
-  {
-    "required": [
-      "accepts"
-    ],
-    "type": "object"
-  },
-  {
-    "required": [
-      "receipt"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "properties": {
+      "after": {
+        "anyOf": [
+          {
+            "description": "hash computed from the content of `after`",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "at": {
+        "anyOf": [
+          {
+            "description": "ISO time of the run",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "before": {
+        "anyOf": [
+          {
+            "description": "hash computed from the content of `before`",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "breaking": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "changes": {
+        "anyOf": [
+          {
+            "items": {},
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "compatible": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "cosmetic": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "error": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "evidence": {
+        "anyOf": [
+          {
+            "description": "every request made, in the order sent: method, url, request headers of note, status, ms; a request that drew no answer has status 0 and its error; one this shelf stopped has status null and says why: timed_out with limit_ms (no answer in 15 s), too_large with limit_bytes, or canceled; a redirect followed is listed in redirects, and a request still unanswered when a report was cut has unanswered: true",
+            "items": {},
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "hash_check": {
+        "anyOf": [
+          {
+            "description": "for each snapshot that came with a hash: supplied, computed, matches",
+            "items": {},
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ok": {
+        "anyOf": [
+          {
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "rules": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "same": {
+        "anyOf": [
+          {
+            "description": "true when the two hashes computed here from the snapshot content are equal",
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "unclassified": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  },
+  {
+    "required": [
+      "accepts"
+    ],
+    "type": "object"
+  },
+  {
+    "required": [
+      "receipt"
+    ],
+    "type": "object"
+  }
+]
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/non-destructive annotations: hashes are recomputed from snapshot content and mismatches are reported but never trusted, nothing is stored between calls (the caller holds history), per-request 15s waits report timed_out instead of the server's answer, and a call cut for time returns nothing. It also discloses the paid per-millisecond pricing and the wallet/line credential path — invocation-critical behavior the annotations do not carry.

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?

Purpose is front-loaded in the first sentence and each subsequent sentence adds a distinct operational fact (hash trust, statelessness, timeout semantics, pricing). It is dense and somewhat run-on, and the payment/pass paragraph, while necessary for a paid tool, consumes a large fraction of the text.

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?

An output schema exists, yet the description still names the change classes and the deciding-rule field an agent will receive, and it fully covers failure modes (timed_out, partial results discarded, hash mismatch) plus the payment prerequisite. Nothing an agent needs in order to invoke this correctly is missing.

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%, and the schema already documents the url/after/before/line roles, so the baseline applies. The description adds the semantic point that `before` may be a full contract answer or its `snapshot` array and that its hash is revalidated, but `line` and the `after`/`url` precedence gain nothing new.

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 and resource — 'Returns every change between two contract snapshots' — plus the exact output taxonomy (breaking / compatible / cosmetic) and the rule attribution. It is clearly distinct from the sibling attest_contract, which produces the snapshots this tool consumes.

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?

Explicitly tells the caller to pass a prior attest_contract answer as `before` and either a later one as `after` or a `url` to fetch fresh, and explains the tradeoff between the two modes (no request, milliseconds vs. three network requests). It stops short of any when-not-to-use guidance or a named alternative for closely adjacent needs.

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

All ZEAM :: Prism 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