mcp-coreclaw

run_workers_batch

Run multiple CoreClaw workers in one call and return a per-item summary (run_slug, status, verdict). Serial by default; optional concurrency.

WHEN TO USE: Use when accepting/validating many workers at once (e.g. full-store smoke test) to avoid many individual run_worker calls. Each item is an ad-hoc run_worker (async). The tool polls each run to a terminal state and returns a summary array. Note: the batch Path is synthetic; the custom handler issues per-item run_worker requests. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。

WHEN NOT TO USE: Do not use public web search or code search for private CoreClaw platform data. Do not call excluded internal worker-version or internal-detail APIs.

RETURNS: JSON: {total, counts, results:[{worker_id, run_slug, status, verdict, err_msg, real_field_count}]}. Items are processed in input order.

WORKFLOW: Call after list_store_workers/list_workers + get_worker_input_schema for each item. Follow with get_worker_run_log on any FAILED/ERROR_RECORD item.

Input Schema

TableJSON Schema

Name	Required	Description
`items`	Yes	JSON array of {worker_id, input_json, version?}. Max 50 items.
`verify`	No	Run verify_run judgment on each succeeded item. (default: true)
`concurrency`	No	Max parallel runs. 1 = serial. (default: 1)
`skip_run_ids`	No	JSON array of run_ids already completed; handler skips polling for items returning one of these and marks SKIPPED. Best-effort: re-submitting ad-hoc input starts a new run, so for exact resume omit completed items from items instead. (optional)
`timeout_seconds`	No	Per-item poll timeout. (default: 180)
`poll_interval_seconds`	No	Seconds between status checks per item. (default: 5)

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only cover readOnly/destructive/idempotent hints, but the description adds substantial behavioral detail: it polls runs to terminal state, uses a synthetic batch path with custom per-item run_worker requests, processes items in input order, and explains skip_run_ids best-effort semantics. This goes well beyond the structured annotations with no contradiction.

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 description is well-organized with clear section headers and front-loaded purpose. However, it includes some extraneous content like the generic Chinese trigger phrase and a broad 'do not use public web search' warning that does not specifically address this tool's usage. Most sentences earn their place, making it only slightly overlong.

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?

Given the tool's complexity (6 parameters, no output schema), the description covers the return JSON shape, processing order, polling behavior, concurrency defaults, and workflow dependencies. It also documents a subtle behavioral caveat about skip_run_ids and ad-hoc runs, making it comprehensive for an agent to use correctly.

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% with per-parameter descriptions, so baseline is 3. The description adds value by explaining that items are ad-hoc run_worker invocations, polling behavior, and the caveat about resubmitting ad-hoc input starting new runs. This extra context justifies a score above baseline.

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 clearly states it runs multiple CoreClaw workers in one call and returns a per-item summary, distinguishing it from the individual run_worker sibling. It specifies the scope (batch of ad-hoc runs), default serial behavior, and optional concurrency.

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?

Explicit WHEN TO USE and WHEN NOT TO USE sections are provided, including a concrete example (full-store smoke test) and the alternative (avoiding many individual run_worker calls). The WORKFLOW section gives clear preceding and succeeding steps, naming specific sibling tools.

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

All mcp-coreclaw 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

A3.7/5.0

Disambiguation3/5

Most tools follow a systematic scope pattern (user's last run, worker's last run, specific run), so intent is discernible, but the reversed word order (e.g., get_last_worker_run vs get_worker_last_run) makes many tools easy to conflate. Descriptions are thorough, yet the sheer number of near-identical names creates real misselection risk.

Naming Consistency3/5

Verbs and nouns are consistently snake_case, but the modifier order alternates unpredictably—some tools say last_worker_run, others worker_last_run—across abort/export/get/list/rerun groups. This inconsistency makes the set feel less coherent than a strict verb_noun pattern would.

Tool Count2/5

At 42 tools, the surface is heavily inflated by triplicating every run-related action across user-last, worker-last, and specific-run scopes. Many of these could be consolidated into a single tool with optional worker_id/run_id parameters, making the count feel excessive for the domain.

Completeness4/5

The surface covers the full lifecycle of workers, runs, tasks, queue, and account, including poll/verify/batch operations that go beyond basic CRUD. Minor gaps exist (e.g., no explicit run-input retrieval, no worker editing), but agents can achieve all common workflows without dead ends.

Resources

Need Help?