session-checkpoint-mcp

Overview Schema Source Related Servers Discussions Admin

Save session checkpoint

save_session_checkpoint

Save a session's goal, progress, modified files, and recent commands to a local checkpoint so work can resume after a crash, /clear, or context limit without re-exploring.

Instructions

Save the current session's goal, progress, touched files and recent commands to this session's checkpoint in the project (.claude-checkpoints/.json, or .claude-checkpoint when the client provides no session id), so a new session can resume after a crash, /clear, or context limit without re-exploring. Call after finishing a milestone, before risky operations, and when the conversation is getting long. Git branch, HEAD and uncommitted files are captured automatically.

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": {
      "goal": "<goal>"
    },
    "name": "save_session_checkpoint"
  }
}

Input Schema

Name	Required	Description	Default
`goal`	Yes	The primary objective of the session, in one or two sentences.
`mode`	No	replace: overwrite the checkpoint. merge: update the existing one, appending commands, decisions and files.	replace
`tasks`	No	Sub-goals with their status. In merge mode, tasks with the same description are updated.
`summary`	No	Where things stand: what works, what is broken, what you were in the middle of.
`decisions`	No	Key decisions, constraints, and dead ends to avoid repeating.
`nextSteps`	No	Concrete next actions, in order, for whoever resumes.
`projectRoot`	No	Absolute path of the project. Defaults to the client's workspace root or the server's working directory.
`modifiedFiles`	No	Files you changed, with an optional note. Uncommitted git changes are detected automatically; list files here to annotate them or to include committed ones.
`recentCommands`	No	Recent significant terminal commands (builds, tests, migrations), oldest first, with exit codes and a short note on the outcome. Secrets are redacted automatically.

Output Schema

Name	Required	Description	Default
`mode`	Yes
`path`	Yes
`bytes`	Yes
`counts`	Yes
`warnings`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.3Nov 7, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations are minimal (write, non-idempotent, non-destructive, closed-world), so the description carries real weight: it discloses the on-disk file layout, the fallback filename when no session id exists, automatic git branch/HEAD/uncommitted-file capture, and automatic secret redaction in commands. It does not cover failure modes, write-permission needs, or what happens if the project path is unwritable.

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?

Three sentences, front-loaded with the action and destination before the usage triggers. Dense but not padded; only the trailing auto-capture sentence could arguably be folded into the file-list discussion.

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?

For a nine-parameter mutation tool with a 100%-covered schema and an output schema, an agent has everything needed to call it correctly: what to pass, when to call it, where output lands, and what is captured for free. Return values need no explanation because an output schema exists.

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; the description adds value by clarifying that git state is captured automatically, which makes modifiedFiles an annotation layer rather than a required inventory, and by explaining the session-id/no-session-id path fallback that has no corresponding schema field. Mode semantics and task merging are already fully documented in the schema, so the gain is incremental.

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 ("Save the current session's goal, progress, touched files and recent commands") plus the exact destination path convention. It also explains the resumption payoff, which distinguishes it from load_session_checkpoint and list_session_checkpoints without naming them.

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 three concrete triggers: after a milestone, before risky operations, and when the conversation gets long, plus the failure scenarios it protects against (crash, /clear, context limit). It never explicitly names load_session_checkpoint as the counterpart or states when not to bother, 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.

Deploy Server