Skip to main content
Glama

Run or resume a checkpointed structured swarm batch

swarm_batch_run
DestructiveIdempotent

Execute or resume a checkpointed structured batch across multiple items with microbatching, partial recovery, and circuit breakers. Use it to run repeatable batch jobs that resume after failures.

Instructions

Execute or resume a checkpointed structured batch (with microbatching, partial recovery, and circuit breakers) across 'auto' (default), 'codebuddy', or 'zcode'.

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": {
      "batchId": "<batchId>",
      "task": "<task>",
      "schema": "<schema>",
      "items": "<items>"
    },
    "name": "swarm_batch_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNo
taskYes
itemsYes
modelNo
schemaYes
backendNo
batchIdYes
profileNo
providerNo
ephemeralNo
maxCreditNo
domainRuleNo
maxRetriesNo
templateIdNo
includeItemsNo
reserveSlotsNo
itemTimeoutMsNo
capacityWaitMsNo
maxConcurrencyNo
microbatchSizeNo
pollIntervalMsNo
maxBatchInputCharsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is partly known. The description adds genuinely useful behavior — checkpointing, microbatching, partial recovery, circuit breakers — but does not explain what 'destructive' means here, how resume is performed, or that batches may consume credit (maxCredit exists in the schema).

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?

A single front-loaded sentence that packs the core action and key resilience features without filler. It is dense but not padded; the only waste is the incomplete backend enumeration, which is a correctness issue rather than verbosity.

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

Completeness2/5

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

For a 22-parameter, nested-object, destructive, credit-consuming batch operation with no output schema and no sibling differentiation, the description is far too thin. An agent would not know how to construct a valid call, what the required task/schema/items relationship is, or what happens to an existing batch on resume.

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

Parameters2/5

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

With 22 parameters at 0% schema description coverage, the description carries almost the entire semantic burden and does not. It mentions the backend dimension but lists only 'auto', 'codebuddy', and 'zcode', omitting the 'qoder' enum value present in the schema, and says nothing about batchId, task, schema, items, maxCredit, ephemeral, profile, or the concurrency/timeout controls.

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?

The description gives a specific verb ('Execute or resume') and resource ('checkpointed structured batch') plus notable features (microbatching, partial recovery, circuit breakers). It does not differentiate itself from close siblings like swarm_run_structured or zcode_batch_run, so an agent cannot tell which batch runner to pick from the text alone.

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

Usage Guidelines2/5

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

The only usage cue is the word 'resume', implying a prior batch can be continued, but it never says when to use this versus swarm_run_structured, zcode_batch_run, or the non-batch runners. No prerequisites, no exclusions, and no guidance on how resumption is triggered (presumably reusing batchId, which is unstated).

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