ZEAM :: Prism

Open and manage a line

line

Opens a line: calls on it spend bought time and carry no payment. op: open {channelId} takes the channelId buy_time returned and answers {nonce, sign}; sign the text in sign with the payer key (EIP-191, personal_sign); prove {channelId, nonce, signature} returns the credential; on, off, status, close {credential}. Time burns only while a call runs; an open websocket subscription burns the whole time it is open. Example: {"op":"open","channelId":""}

Input Schema

Name	Required	Description
`op`	Yes	open, prove, on, off, status or close
`nonce`	No	optional string — prove
`channelId`	No	optional string — open and prove
`signature`	No	optional string — prove
`credential`	No	optional string — on, off, status, close

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 15, 2026

removedInput schema / $schema

Removed value: -"https://json-schema.org/draft/2020-12/schema"

changedInput schema / properties / channelId / description

Previous value: -"the channel that pays; open and prove"New value: +"optional string — open and prove"

changedInput schema / properties / credential / description

Previous value: -"the credential prove returned; on, off, status, close"New value: +"optional string — on, off, status, close"

changedInput schema / properties / nonce / description

Previous value: -"the nonce open returned; prove"New value: +"optional string — prove"

changedInput schema / properties / signature / description

Previous value: -"the payer key over the message open returned; prove"New value: +"optional string — prove"

removedOutput schema / $schema

Removed value: -"https://json-schema.org/draft/2020-12/schema"

removedOutput schema / additionalProperties
```
Removed value: -{}
```

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "channelId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "credential": {
+        "anyOf": [
+          {
+            "description": "send as x-line or _meta[\"zeam-pass/line\"]",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "metering": {
+        "anyOf": [
+          {
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "msRemaining": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "msReturned": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "msSpent": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "nonce": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "op": {
+        "anyOf": [
+          {
+            "description": "challenge, opened, on, off, status, closed or line_failed",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "sign": {
+        "anyOf": [
+          {
+            "description": "the message to sign with the payer key",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  },
+  {
+    "required": [
+      "accepts"
+    ],
+    "type": "object"
+  },
+  {
+    "required": [
+      "receipt"
+    ],
+    "type": "object"
+  }
+]

removedOutput schema / properties

Removed value: -{
-  "channelId": {
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "credential": {
-    "anyOf": [
-      {
-        "description": "send as x-line or _meta[\"zeam-pass/line\"]",
-        "type": "string"
-      },
-      {
-        "type": "null"
-      }
-    ]
-  },
-  "metering": {
-    "type": [
-      "boolean",
-      "null"
-    ]
-  },
-  "msRemaining": {
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "msReturned": {
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "msSpent": {
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "nonce": {
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "op": {
-    "anyOf": [
-      {
-        "description": "challenge, opened, on, off, status, closed or line_failed",
-        "type": "string"
-      },
-      {
-        "type": "null"
-      }
-    ]
-  },
-  "sign": {
-    "anyOf": [
-      {
-        "description": "the message to sign with the payer key",
-        "type": "string"
-      },
-      {
-        "type": "null"
-      }
-    ]
-  }
-}

AddedOct 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare a non-read-only, open-world, non-idempotent operation, and the description adds genuinely new context: a payer key must sign the returned text using EIP-191 personal_sign, and time burns only while a call runs while an open websocket subscription burns for its whole duration. What it does not explain is the effect of on/off/close (does close settle, refund, or invalidate the credential?), which is the main behavioral gap.

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?

Extremely dense and front-loaded: the economic invariant comes first, then the op sequence, then the burn semantics, then a concrete JSON example. The telegraphic phrasing ('op: open {channelId} takes the channelId buy_time returned', naming 'sign' where the schema uses 'signature') costs a little readability but almost nothing is wasted.

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?

An output schema exists, so return values need no explanation, and the description supplies the auth/flow context that the annotations and schema cannot. For a 5-parameter, six-operation lifecycle tool, the only shortfall is that the on/off/status operations are named but never described.

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 goes beyond it by explaining provenance (channelId is the value buy_time returned) and by grouping parameters per op (prove consumes channelId, nonce, signature; on/off/status/close consume credential). It does not clarify the nonce's origin or format, and it refers to a 'sign' field that the schema calls 'signature'.

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?

The description states a concrete resource (a payment line) and enumerates the six operations it multiplexes: open, prove, on, off, status, close. It also distinguishes the tool's economics from its sibling by noting that calls on a line 'spend bought time and carry no payment', pointing at buy_time as the source of the channelId.

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?

The lifecycle is spelled out as an ordered sequence (open -> sign with payer key -> prove -> on/off/status/close), and 'op: open {channelId} takes the channelId buy_time returned' tells the agent to call buy_time first. There is no explicit when-not guidance or error/precondition handling, so it stops short of a 5.

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

All ZEAM :: Prism tools Inspect

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

Need Help?