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

Name	Required	Description
`body`	No	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'.
`step`	No	ENVELOPE. Optional short step label. Example: 'step-3'.
`files`	No	ENVELOPE. File references or paths — references, not contents. Contents go in `body`. Example: '[]'.
`risks`	No	ENVELOPE. Known risks. Example: '[]'.
`scope`	Yes	The unit of work. Alias: workflow_id. Namespace-scoped. Example: 'permit-review-2026-08'.
`state`	No	BODY, OPAQUE. Free-form resume state, never parsed. Example: '{"cursor":"abc"}'.
`due_by`	No	ENVELOPE. ISO-8601 deadline for the work, if it has one. Example: '2026-08-20T00:00:00Z'.
`status`	No	ENVELOPE. Where the work stands, e.g. in_progress / blocked / waiting / done. Your vocabulary; we do not interpret it. Example: 'in_progress'.
`evidence`	No	ENVELOPE. References supporting the verified state. Example: '[]'.
`priority`	No	ENVELOPE. 0 (highest) to 9. Example: '5'.
`agent_key`	No	Your agent_secret, if your MCP host cannot set the Authorization header. Prefer the header.
`artifacts`	No	ENVELOPE. Artifact references produced so far (ids, URLs). Example: '[]'.
`objective`	Yes	ENVELOPE. REQUIRED. The goal, as currently stated. <=2048 chars. Example: 'Decide whether permit P-1 is a sales opportunity'.
`remaining`	No	ENVELOPE. What still has to be done. Example: '["price it","draft the email"]'.
`tools_used`	No	ENVELOPE. Tools already called, so the next invocation does not redo the work. Example: '[]'.
`next_action`	Yes	ENVELOPE. REQUIRED. The single next step, concretely. Alias: next_step. <=2048 chars. Example: 'Call the pricing API for SKU-88 and compare to quote'.
`ttl_seconds`	No	Retention. Default 2592000 (30d), max 7776000 (90d). Example: '2592000'.
`dependencies`	No	ENVELOPE. What this work depends on. Example: '[]'.
`privacy_mode`	No	'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_questions`	No	ENVELOPE. Unresolved questions blocking or shaping the work. Example: '[]'.
`verified_state`	No	ENVELOPE. A SHORT summary of what was actually CONFIRMED (not assumed). Put the detail in `body`. Example: '{"permit_fetched":true}'.
`provider_extras`	No	BODY, OPAQUE. Vendor/framework-specific state. Stored and returned verbatim, never interpreted. Example: '{}'.
`budget_remaining`	No	ENVELOPE. Whatever budget means for you — calls, tokens, USDC. Example: '{"usdc":"0.05"}'.

TDQS

A4.6/5.0

Behavior5/5

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

The description goes well beyond the annotations, disclosing that the tool is FREE, that the BODY fields are 'never parsed, indexed or logged in any mode,' that privacy_mode 'client_key' means the provider cannot read the body, and that authentication can be via Authorization header or agent_key. The HTTP route is also provided. These are significant behavioral traits not visible in annotations, and 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 dense and well-structured, with key concepts highlighted (ENVELOPE, BODY, FREE, REQUIRED) and information front-loaded. It contains some redundancy ('FREE' appears twice) and is slightly long, but every sentence carries useful information about behavior, constraints, or security, so the length is justified.

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 23-parameter, write-side tool with no output schema, the description is exceptionally complete. It explains the envelope/body architecture, required fields, size guidance, privacy modes, authentication, HTTP route, and the tool's relationship to resume_packet. This covers all key aspects an agent needs to invoke it correctly.

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 semantic value by explaining the ENVELOPE vs BODY distinction, the requirement for objective/next_action, and the 'schema is the guardrail' rationale. It also clarifies privacy_mode behavior and ttl_seconds retention. This meaningfully augments the schema descriptions without duplicating them.

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 clearly states the tool's function: 'Save where the work got to, in a STRUCTURED shape so the next invocation can actually act on it.' It uses a specific verb ('save') and resource ('work state'), and distinguishes itself from the sibling tool resume_packet by noting the envelope is what resume_packet synthesizes from. This provides clear differentiation from the read/resume side.

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 context on when to use this tool (to checkpoint structured work state for the next invocation) and implies it is the write counterpart to checkpoint_get/resume_packet. It also provides practical guidance: 'Work state is small: aim for a few kilobytes,' and warns that vague checkpoints are refused. However, it does not explicitly name alternative tools or state when not to use it.

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

All MCPFax Agent Continuity tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Every tool targets a clearly distinct mechanism—barriers, budgets, checkpoints, claims, heartbeats, inboxes, leases, work queues, etc. Even closely related pairs like claim/complete, work_done/inbox_ack, and barrier_status/work_status are explicitly differentiated in their descriptions, so an agent can reliably select the right tool.

Naming Consistency4/5

The dominant pattern is object_verb (e.g., checkpoint_get, work_push, seen_add, lease_release), which is consistent and readable. A few single-word verbs (claim, complete, send) and noun-only names (resume_packet, retry_state, whoami) break the pattern, but they are few and still intuitive.

Tool Count2/5

With 33 tools, the surface is well beyond the 25-tool threshold for 'too many' and will feel heavy for agents to explore, even though the tools are organized into subdomains. The scope is broad, but the sheer number makes the server less approachable and increases the chance of misselection.

Completeness5/5

The tool set provides thorough lifecycle coverage across its domains: checkpoints get/put, work queue push/take/done/fail/status, inbox poll/ack/nack/schedule, lease acquire/renew/release, barrier create/signal/status, dedup add/check, watermark get/set, retry state, budget check/record, and idempotency claim/complete. There are no obvious dead ends or missing essential operations.

Resources

Need Help?