Skip to main content
Glama

Yardstick ATS

Confirm bulk automation rule changes

yardstick_automation_rules_bulk
DestructiveIdempotent

Switch rules on, off or delete them. First use mode=preview with rule_ids or filter. Show the affected rules and skipped rules to the user and get explicit confirmation BEFORE applying. Then use mode=apply with only the exact rule_ids returned by preview; never reapply the filter. Rules that need a step or fail activation validation are skipped when switching on. Show each skipped rule's reason. Warn that shared pipeline rules change for every job on that pipeline, including jobs outside the filter.

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": {
      "action": "<action>",
      "mode": "<mode>"
    },
    "name": "yardstick_automation_rules_bulk"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
actionYes
filterNo
rule_idsNo
request_idNo
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds behavior beyond that: partial-success semantics (rules needing a step or failing activation validation are skipped when switching on), the requirement to surface each skip reason, and the blast-radius warning that shared pipeline rules affect every job on that pipeline including jobs outside the filter.

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?

Front-loads the action, then the preview/apply workflow, then edge-case behavior and the blast-radius warning — a logical order with no filler sentences. It is dense at six sentences, and the pipeline warning might serve better placed earlier, but every sentence contributes operational information.

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

Completeness4/5

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

For a destructive bulk mutation with no output schema and six parameters, the description covers the workflow, confirmation gate, partial-failure handling, and side effects well enough to call it correctly. Remaining gaps are the undocumented `request_id`/`idempotency_key` semantics and a precise account of what preview returns, though the affected/skipped rule split is described conceptually.

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 description coverage is 0%, so the description must carry the load, and it does explain the two most consequential parameters: `mode` as a preview/apply gate and the rule_ids-versus-filter distinction with the constraint that apply must use preview-returned IDs only. It leaves `request_id` and `idempotency_key` unexplained, and the six filter fields are only inferable from their names, so a gap remains despite strong coverage of the critical 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?

Opens with a specific verb set and resource: "Switch rules on, off or delete them," which maps directly to the action enum and makes the bulk nature evident alongside the preview/apply modes. It does not explicitly differentiate itself from the sibling `yardstick_automation_rules_delete` or the standalone `yardstick_automation_rules_preview`, and the internal `mode=preview` could be confused with that separate preview tool, so the sibling boundary is left implicit.

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?

Gives an explicit two-step procedure — use `mode=preview` first with `rule_ids` or `filter`, obtain explicit user confirmation, then call `mode=apply` with only the preview-returned IDs. It states a hard exclusion ("never reapply the filter") and names the confirmation precondition, which is exactly the when-and-how guidance an agent needs for a destructive bulk operation.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.