MCPFax Agent Continuity

Mark a work item finished

work_done

DestructiveIdempotent

Complete an item you hold. FREE. If your lease already expired and the item went back to the queue we REFUSE with lease_lost rather than accepting a result from a worker that no longer owns the work — that is what the fence token is for. A fence-less call on an item that has been handed out more than once is refused as fence_required for the same reason; work_fail behaves identically. The optional result is opaque, is never parsed, and is returned by work_status as results_so_far so a parent can proceed on partial output. 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/work/done.

Input Schema

TableJSON Schema

Name	Required	Description
`fence`	No	The fence token from work_take, for THIS item. Checked exactly when supplied; when omitted we accept the call only while the item has been handed out exactly once, and otherwise refuse with fence_required. Every item on a queue draws its own token independently, so the fence you hold for one item is not one step away from the fence another worker holds for another. The example below is a shape, not a usable value. Example: '3170294857216913'.
`result`	No	Optional opaque outcome, <=8192 bytes. Never parsed or indexed. Example: '{"ok":true}'.
`item_id`	Yes	The item you were given. Example: 'P-1'.
`queue_id`	Yes	The queue. Alias: job_id. Example: 'permit-batch-2026-08'.
`agent_key`	No	Your agent_secret, if your MCP host cannot set the Authorization header. Prefer the header.

TDQS

A4.4/5.0

Behavior5/5

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

The description goes well beyond annotations, explaining the lease_lost and fence_required refusal cases, the opaque and never-parsed nature of the result, how the result surfaces via work_status, the cost (FREE), and authentication requirements. This provides extensive behavioral context for a mutation/destructive tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph that repeats 'FREE' twice and includes an HTTP route, which is not essential for MCP invocation. It front-loads the main purpose well but could be tightened without losing key safety and refusal details.

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 complex mutation with no output schema, the description covers when to use, error conditions, result behavior, authentication, and cost. It does not specify what the direct response from work_done is on success, but given the rich context and idempotent annotation, it is largely complete.

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?

While the schema already documents all 5 parameters with 100% coverage, the description adds critical semantic context for fence (why it exists, what happens without it) and result (opaque, returned via work_status). This raises the value beyond the schema's plain definitions.

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 'Complete an item you hold,' which clearly states the action and target. It further clarifies that this is for finishing a work item successfully, and distinguishes itself from work_fail by noting identical refusal behavior for fence-less calls, implying the success/failure split.

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?

It explicitly states when to use (when you hold the item and want to mark it done) and describes failure conditions (lease expired, fence token mismatches). It references work_fail for comparison but does not explicitly say 'use work_fail for failures,' so it lacks a direct alternative recommendation.

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?