CueFrame

Get Checkpoint

get_checkpoint

Read-onlyIdempotent

Read a checkpoint packet — the durable approval unit a held compose pauses at (wait_job reports awaiting_input with {checkpointId, stage, version}). Carries the stage artifact, presigned storyboard stills (REVIEW THE EVIDENCE, not raw JSON), critic verdicts, the money triple {thisStepUsd, jobSpendSoFarUsd, estimatedJourneyTotalUsd} to relay to your human, and the recorded decision once resolved. When the Brief's gates set reviewMode:'hosted' the packet also carries reviewUrl — a browser review page where your human decides directly (relay THAT link instead of raw stills; you learn the decision via checkpoint webhooks / wait_job). Answer an awaiting packet with resume(checkpointId, ...).

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": {
      "checkpointId": "<checkpointId>"
    },
    "name": "get_checkpoint"
  }
}

Input Schema

Name	Required	Description	Default
`checkpointId`	Yes	checkpointId (path).

Output Schema

Name	Required	Description
`id`	No
`kind`	No
`quote`	No
`stage`	No
`status`	No
`briefId`	No
`version`	No
`artifact`	No	The stage artifact under review: the locked ComposePlan at content; the composition wire shape at layout/motion; the judged composition snapshot on kind:'score'.
`decision`	No	The recorded decision {decision, comments?, globalNote?, decidedAt} once resolved.
`createdAt`	No
`projectId`	No
`reviewUrl`	No	Hosted review-page URL (present when reviewMode is 'hosted') — a human decides from this link, no account or agent session; the recorded decision rides the SAME resume rail, and the agent learns of it via checkpoint webhooks / wait_job.
`stillUrls`	No	Presigned storyboard/eval stills — the packet's visual evidence (may be GC'd by the retention sweep after the job goes terminal; the decision record is immortal).
`updatedAt`	No
`reviewMode`	No	How this packet is decided (from the Brief's gates). 'hosted' = the review PAGE captures the decision; absent/'agent' = the decision flows back through the driving agent.
`composeJobId`	No
`revisionCycle`	No	Revise cycles this gate has consumed. The brief quote states the included count (revisionCyclesIncluded); beyond it, resume(revise) is refused with a typed error.
`criticVerdicts`	No	Per-criterion scores + critique from the design loop / judge, incl. lock_violation entries.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 10, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds substantial context beyond that: the packet carries presigned stills (with the instruction to review evidence rather than raw JSON), critic verdicts, the three cost figures to surface to a human, and the recorded decision once resolved. It also discloses how resolution is learned (webhooks / wait_job), which is real behavioral information no annotation covers.

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 definition is front-loaded and the parenthetical enrichment (stills must be reviewed visually, hosted review link preferred over stills) is actionable rather than filler. It is dense and long for a one-parameter read, so some trimming is possible, but each clause carries operational guidance.

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?

An output schema exists, so return shape needn't be spelled out, yet the description still gives the agent what the schema can't: how to interpret the contents, which link to relay to a human, and how the decision is subsequently delivered. Nothing needed to call this correctly is missing.

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% for the single parameter, so the baseline is 3; the description adds genuine value by specifying the provenance of checkpointId (it comes from wait_job's awaiting_input result) and by pairing it with resume(checkpointId, ...), showing how the same identifier is reused.

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?

Opens with a specific verb and resource ('Read a checkpoint packet') and immediately defines the resource as 'the durable approval unit a held compose pauses at', which distinguishes it from list_checkpoints and wait_job. It then enumerates the packet's contents, so an agent knows exactly what it gets back before opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the trigger condition ('wait_job reports awaiting_input with {checkpointId, stage, version}') and the required follow-up ('Answer an awaiting packet with resume(checkpointId, ...)'). It also branches on the Brief's gates setting reviewMode:'hosted', telling the agent to relay reviewUrl instead of raw stills, and routes decision discovery to checkpoint webhooks / wait_job.

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

All CueFrame tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.