Skip to main content
Glama

MCPFax Agent Continuity

Checkpoint the work

checkpoint_put
Idempotent

Save where the work got to, in a STRUCTURED shape so the next invocation can actually act on it. FREE. objective and next_action are REQUIRED and a checkpoint without them is refused — a vague checkpoint produces a vague briefing, so the schema is the guardrail. Work state is small: aim for a few kilobytes, not a transcript. The ENVELOPE (objective, next_action, status, files, risks and the rest) is cleartext and is what resume_packet synthesizes from. The BODY (body, state, provider_extras) is opaque — never parsed, indexed or logged in any mode. Set privacy_mode:'client_key' and encrypt the body yourself if it is sensitive; we then cannot read it and never hold your key. FREE — this tool never charges. Authenticate with Authorization: Bearer , or pass agent_key as an argument if your host cannot set headers. Equivalent HTTP route: POST /v1/checkpoint/put.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoBODY, OPAQUE. Full context, reasoning, file contents — anything sensitive. Never parsed, indexed or logged in any mode. Send ciphertext here with privacy_mode:'client_key'. Example: 'Full context for the next step, or ciphertext.'.
stepNoENVELOPE. Optional short step label. Example: 'step-3'.
filesNoENVELOPE. File references or paths — references, not contents. Contents go in `body`. Example: '[]'.
risksNoENVELOPE. Known risks. Example: '[]'.
scopeYesThe unit of work. Alias: workflow_id. Namespace-scoped. Example: 'permit-review-2026-08'.
stateNoBODY, OPAQUE. Free-form resume state, never parsed. Example: '{"cursor":"abc"}'.
due_byNoENVELOPE. ISO-8601 deadline for the work, if it has one. Example: '2026-08-20T00:00:00Z'.
statusNoENVELOPE. Where the work stands, e.g. in_progress / blocked / waiting / done. Your vocabulary; we do not interpret it. Example: 'in_progress'.
evidenceNoENVELOPE. References supporting the verified state. Example: '[]'.
priorityNoENVELOPE. 0 (highest) to 9. Example: '5'.
agent_keyNoYour agent_secret, if your MCP host cannot set the Authorization header. Prefer the header.
artifactsNoENVELOPE. Artifact references produced so far (ids, URLs). Example: '[]'.
objectiveYesENVELOPE. REQUIRED. The goal, as currently stated. <=2048 chars. Example: 'Decide whether permit P-1 is a sales opportunity'.
remainingNoENVELOPE. What still has to be done. Example: '["price it","draft the email"]'.
tools_usedNoENVELOPE. Tools already called, so the next invocation does not redo the work. Example: '[]'.
next_actionYesENVELOPE. REQUIRED. The single next step, concretely. Alias: next_step. <=2048 chars. Example: 'Call the pricing API for SKU-88 and compare to quote'.
ttl_secondsNoRetention. Default 2592000 (30d), max 7776000 (90d). Example: '2592000'.
dependenciesNoENVELOPE. What this work depends on. Example: '[]'.
privacy_modeNo'none' (default; body stored as given, still never introspected) or 'client_key' (you encrypted it; we cannot read it and never hold your key). 'escrow' is reserved and not enabled. Example: 'none'.
open_questionsNoENVELOPE. Unresolved questions blocking or shaping the work. Example: '[]'.
verified_stateNoENVELOPE. A SHORT summary of what was actually CONFIRMED (not assumed). Put the detail in `body`. Example: '{"permit_fetched":true}'.
provider_extrasNoBODY, OPAQUE. Vendor/framework-specific state. Stored and returned verbatim, never interpreted. Example: '{}'.
budget_remainingNoENVELOPE. Whatever budget means for you — calls, tokens, USDC. Example: '{"usdc":"0.05"}'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / agent_key / examples
      Added value: +[
      +  "the agent_secret that register returned"
      +]
    • changedInput schema / properties / body / description
      Previous value: -"BODY, OPAQUE. Full context, reasoning, file contents — anything sensitive. Never parsed, indexed or logged in any mode. Send ciphertext here with privacy_mode:'client_key'."New value: +"BODY, OPAQUE. Full context, reasoning, file contents — anything sensitive. Never parsed, indexed or logged in any mode. Send ciphertext here with privacy_mode:'client_key'. Example: 'Full context for the next step, or ciphertext.'."
    • addedInput schema / properties / body / examples
      Added value: +[
      +  "Full context for the next step, or ciphertext."
      +]
  2. Changed21 schema fields changed
    • addedInput schema / properties / artifacts / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / budget_remaining / examples
      Added value: +[
      +  "{\"usdc\":\"0.05\"}"
      +]
    • addedInput schema / properties / dependencies / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / due_by / examples
      Added value: +[
      +  "2026-08-20T00:00:00Z"
      +]
    • addedInput schema / properties / evidence / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / files / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / next_action / examples
      Added value: +[
      +  "Call the pricing API for SKU-88 and compare to quote"
      +]
    • addedInput schema / properties / objective / examples
      Added value: +[
      +  "Decide whether permit P-1 is a sales opportunity"
      +]
    • addedInput schema / properties / open_questions / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / priority / examples
      Added value: +[
      +  5
      +]
    • addedInput schema / properties / privacy_mode / examples
      Added value: +[
      +  "none"
      +]
    • addedInput schema / properties / provider_extras / examples
      Added value: +[
      +  "{}"
      +]
    • addedInput schema / properties / remaining / examples
      Added value: +[
      +  "[\"price it\",\"draft the email\"]"
      +]
    • addedInput schema / properties / risks / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / scope / examples
      Added value: +[
      +  "permit-review-2026-08"
      +]
    • addedInput schema / properties / state / examples
      Added value: +[
      +  "{\"cursor\":\"abc\"}"
      +]
    • addedInput schema / properties / status / examples
      Added value: +[
      +  "in_progress"
      +]
    • addedInput schema / properties / step / examples
      Added value: +[
      +  "step-3"
      +]
    • addedInput schema / properties / tools_used / examples
      Added value: +[
      +  "[]"
      +]
    • addedInput schema / properties / ttl_seconds / examples
      Added value: +[
      +  2592000
      +]
    • addedInput schema / properties / verified_state / examples
      Added value: +[
      +  "{\"permit_fetched\":true}"
      +]
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only provide readOnly=false, idempotent=true, destructive=false. The description adds substantial behavioral detail: checkpoints without objective/next_action are refused, the body is never parsed/indexed/logged in any mode, privacy_mode:'client_key' means the service cannot read the body and never holds the key, the tool is free, and auth can be a bearer header or agent_key argument. There is no contradiction with the annotations.

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?

The description is front-loaded with the core purpose and each sentence carries real operational information: required fields, size, envelope/body behavior, privacy, auth, and route. It is slightly redundant because 'FREE' appears twice, and the cleartext-envelope detail partially repeats what the schema field tags already say. Overall it is dense but not bloated.

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?

For a 23-parameter tool with no output schema, the description covers the invocation contract thoroughly: what to save, what is required, how to keep data private, how to authenticate, and how the envelope feeds resume_packet. The main gap is that it never states what the call returns, such as an acknowledgement or checkpoint id, which would help with no output schema present.

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 individual parameters are already documented. The description adds valuable cross-cutting semantics: the envelope/opaque-body distinction, why objective and next_action are enforced, the size guidance, and the confidentiality contract for body/privacy_mode. This raises it above the baseline 3 because it helps the agent know how to treat the parameter groups, not just what each field is.

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 opens with a precise verb and resource: 'Save where the work got to, in a STRUCTURED shape so the next invocation can actually act on it.' It also differentiates from siblings by explaining that the envelope is what resume_packet synthesizes from, and that the body is opaque. This makes it immediately distinct from checkpoint_get, work_push, and resume_packet.

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 description gives clear operational context: it is for persisting a structured checkpoint for the next invocation, with objective and next_action required, and it explains auth options and the HTTP route. However, it does not explicitly say when not to use it or name alternatives like checkpoint_get or work_status; the relationship to resume_packet is implied rather than a stated selection rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources