Resume-effect reconciliation for checkpointed agent runs

resume_record_effect

Record (backfill) an effect in your account's ledger (POST /effects).

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": {
      "run_id": "<run_id>",
      "checkpoint_ns": "<checkpoint_ns>",
      "node": "<node>",
      "effect_key": "<effect_key>",
      "kind": "<kind>"
    },
    "name": "resume_record_effect"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	Yes
`node`	Yes
`landed`	No
`result`	No
`run_id`	Yes
`effect_key`	Yes
`checkpoint_ns`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

C2.6/5.0

Behavior2/5

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

No annotations are provided, so the description must carry behavioral details. It identifies a POST write endpoint but omits permissions, idempotency or duplicate handling, reversibility, and response behavior for a mutation.

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?

One front-loaded sentence with no filler. However, it is extremely terse relative to a seven-parameter mutation, making the sizing questionable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No annotations, no output schema, 0% parameter coverage, and a nested object parameter create high complexity. A single sentence with no parameter or behavioral detail is not enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Seven parameters with zero schema description coverage. The description supplies no meanings for run_id, checkpoint_ns, node, effect_key, kind, landed, or result, so it adds nothing beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (record/backfill), resource (effect), and endpoint (POST /effects), so the basic purpose is clear. It does not distinguish itself from sibling resume_execute_effect, so it falls short of a 5.

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

Usage Guidelines3/5

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

The word 'backfill' implies the tool is for retroactive recording, giving some usage context. It never names when to use it instead of resume_execute_effect or other siblings, so guidance remains implicit.

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

All Resume-effect reconciliation for checkpointed agent runs 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.

Resources

Need Help?