callimachus

Overview Schema Source Related Servers Discussions Admin

snapshot_session

Save a resumable checkpoint of a thread with its transcript, decisions, gotchas, and TODOs before context compaction or agent handoff; returns the snapshot ID.

Instructions

Save a resumable checkpoint of a thread (packed transcript plus the project's decisions, gotchas and TODOs) before context compaction or a handoff to another agent. Returns the snapshot id.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "thread_id": "<thread_id>"
    },
    "name": "snapshot_session"
  }
}

Input Schema

Name	Required	Description	Default
`label`	No	Snapshot label (defaults to the thread title).
`thread_id`	Yes	Thread id to checkpoint.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.11.4Nov 11, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "createdAt": {
+          "type": "integer"
+        },
+        "id": {
+          "type": "integer"
+        },
+        "label": {
+          "type": "string"
+        },
+        "projectPath": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "sourceKind": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "threadId": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "tokenEstimate": {
+          "type": "integer"
+        }
+      },
+      "required": [
+        "id",
+        "threadId",
+        "projectPath",
+        "sourceKind",
+        "label",
+        "tokenEstimate",
+        "createdAt"
+      ],
+      "type": "object"
+    },
+    {
+      "properties": {
+        "notice": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "notice"
+      ],
+      "type": "object"
+    }
+  ],
+  "type": "object"
+}

Changed4 schema fields changedv0.11.3Nov 6, 2026

removedInput schema / $schema

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

changedInput schema / properties / label / description

Previous value: -"Optional label for the snapshot; defaults to the thread title."New value: +"Snapshot label (defaults to the thread title)."

changedInput schema / properties / thread_id / description

Previous value: -"The thread id (from a search/recent result) to checkpoint."New value: +"Thread id to checkpoint."

removedInput schema / title
```
Removed value: -"SnapshotArgs"
```

Addedv0.6.2Jun 23, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Annotations already declare the mutation profile (readOnly=false, destructive=false, idempotent=false), so the lower bar applies. The description adds useful context about what is captured and that a snapshot id is returned, but says nothing about whether repeat calls accumulate snapshots, storage limits, or permissions.

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?

Two sentences, front-loaded with the action and payload, closing with the return value. No filler or restatement of the title.

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?

A two-parameter mutation tool with an output schema; the description covers intent, timing, contents and the returned id, and the annotations cover the safety/idempotency profile. Nothing an agent needs to invoke it 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 both parameters are documented there, including the label defaulting to the thread title. The description adds no meaning beyond the schema, so the baseline 3 applies.

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?

Uses a specific verb+resource ("Save a resumable checkpoint of a thread") and further enumerates the payload — packed transcript plus decisions, gotchas and TODOs — which also implicitly separates it from load_snapshot and list_snapshots.

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 an explicit triggering condition: "before context compaction or a handoff to another agent." It omits an explicit when-not or named alternative (e.g. resume via load_snapshot), so it stops short of full routing guidance.

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