Skip to main content
Glama

Tomorrow Lives Engines

by com.tomorrowlives
OverviewDiscussionsAdmin

Replay a session

pull_replay

Recomputes a session's hashes against those recorded with it and, for a twin session, runs the twin again from what it records: replays is true when everything matches. A session that does not replay is a finding, not a refused input: it answers 200 with ok false, replays false and which of the hashes did not match. Costs 1 unit, a session that does not replay included.

Input Schema

NameRequiredDescriptionDefault
sessionYesThe session document to recompute, as JSON.

Output Schema

NameRequiredDescriptionDefault
msNoMilliseconds the run took.
jobYesThe job id; the job tool reads it.
verbNoThe tool that made it.
filesNoFiles made, each with a name, type, size and a signed URL.
unitsNoUnits this call cost.
resultNoThe engine's own answer, a JSON document.
statusNoqueued when the job runs in the background.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / session / description
      Added value: +"The session document to recompute, as JSON."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "files": {
+      "description": "Files made, each with a name, type, size and a signed URL.",
+      "items": {
+        "additionalProperties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "job": {
+      "description": "The job id; the job tool reads it.",
+      "type": "string"
+    },
+    "ms": {
+      "description": "Milliseconds the run took.",
+      "type": "number"
+    },
+    "result": {
+      "description": "The engine's own answer, a JSON document."
+    },
+    "status": {
+      "description": "queued when the job runs in the background.",
+      "type": "string"
+    },
+    "units": {
+      "description": "Units this call cost.",
+      "type": "number"
+    },
+    "verb": {
+      "description": "The tool that made it.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "job"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

With annotations only covering the safety flags (readOnly=false, idempotent=false), the description carries substantial extra context: it re-runs a twin (explaining the non-read-only, non-idempotent hints), reports which hashes failed, answers 200 with ok=false instead of erroring, and discloses a cost of 1 unit even on failure. Cost and failure-mode disclosure go well beyond what the schema and annotations provide.

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?

Two dense sentences with no filler: the mechanical behavior comes first, then the outcome and cost semantics. The phrasing is slightly convoluted ('runs the twin again from what it records'), but nothing is padding and the key facts are front-loaded.

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, so return-value documentation is not required, yet the description still explains the ok/replays outcomes and the partial-match reporting. Combined with the cost notice and the twin re-run behavior, an agent has everything needed to call this correctly and interpret the result.

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?

There is a single parameter ('session') whose schema description coverage is 100%, so the schema already documents it as the session document to recompute. The description adds no format, size, or sourcing detail beyond that. Baseline 3 applies when the schema does the heavy lifting.

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 states a concrete verb and resource: recompute a session's recorded hashes and replay a twin session. An agent can tell this apart from most pull_* siblings (align, analyse, seal, close). It stops short of naming the sibling that creates the twin (pull_twin) or otherwise routing between them, so sibling differentiation is implicit rather than explicit.

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?

Usage is implied rather than stated: it clarifies that a non-replaying session is a legitimate 'finding' rather than a rejected input, which shapes expectations. But there is no explicit when-to-use guidance, no prerequisites for having a session document or a twin, and no direction to alternatives among the many pull_* tools.

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

All Tomorrow Lives Engines 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