Skip to main content
Glama

batch_prepare

DestructiveIdempotent

Prepare independent production repeats from one validated seed-variable template by creating immutable per-sample snapshots, then use batch_submit to record dispatch intent.

Instructions

Prepare independent production repeats using one validated seed-variable template. samples: [{sample_id,seed}]. Uses existing validation, creates immutable per-sample snapshots and no preflight jobs. Call batch_submit to persist dispatch intent.

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": {
      "task_id": "<task_id>",
      "revision": "<revision>",
      "plan_id": "<plan_id>",
      "snapshot_id": "<snapshot_id>",
      "samples": "<samples>",
      "op_id": "<op_id>"
    },
    "name": "batch_prepare"
  }
}

Input Schema

NameRequiredDescriptionDefault
op_idYes
tokenNo
plan_idYes
samplesYes
task_idYes
revisionYes
snapshot_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

The description adds real context beyond the annotations: it reuses existing validation, creates immutable per-sample snapshots, and skips preflight jobs. But destructiveHint=true is never explained or reconciled with 'creates immutable per-sample snapshots', so an agent cannot tell what is at risk. The meaning of op_id (plausibly an idempotency key given idempotentHint) and token is also left undisclosed.

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?

Roughly three sentences, front-loaded with the core action and ending with the next step, with no filler. It loses a point for fragmented, cryptic phrasing such as 'no preflight jobs', which costs the reader more parsing effort than a clear clause would.

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

Completeness3/5

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

The output schema exists, so return values need not be explained. For a 7-parameter, destructive, multi-step tool, though, the definition omits the relationships among plan_id, snapshot_id, revision, and op_id, and never says what a prepared snapshot depends on. Adequate as a pointer, insufficient as an operating manual given 0% schema coverage.

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

Parameters3/5

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

Schema description coverage is 0% across 7 parameters, so the description must compensate and largely does not: task_id, revision, plan_id, snapshot_id, op_id, and token get no meaning at all. Credit for specifying the samples shape as [{sample_id,seed}], which is genuinely useful since samples is an unconstrained array of free-form objects. That single disclosure does not cover the remaining six required parameters.

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 and resource: 'Prepare independent production repeats using one validated seed-variable template.' That is concrete enough to distinguish it from batch_submit (which the description explicitly routes to for persistence) and from run_prepare. It is terse and jargon-heavy ('production repeats', 'seed-variable template'), but an agent can tell what kind of operation this is without 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 Guidelines3/5

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

The closing sentence 'Call batch_submit to persist dispatch intent' establishes sequencing in a two-step workflow, which is genuine guidance. However, there is no statement of when this tool should not be used, no differentiation from the sibling run_prepare, and no prerequisites (e.g., must a plan and snapshot already exist?) despite plan_id and snapshot_id being required.

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