Skip to main content
Glama
dcfg-mcp

dcfg-mcp

classify_procedure

Classify a data center task as SOP, MOP, or EOP and identify missing procedure details such as back-out plans, approvals, and points of no return.

Instructions

Classify a data center task as SOP, MOP or EOP and list what the paper is missing.

EOP: a service or person is in danger now; it stops at the first safe state. MOP: the work changes redundancy or switching topology; it needs a Point of No Return, a back-out plan and approval before work. SOP: a repeatable routine that never changes redundancy. A Permit to Work is an administrative gate, not a fourth procedure.

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_description": "<task_description>",
      "service_or_person_in_danger_now": "<service_or_person_in_danger_now>",
      "changes_redundancy_or_topology": "<changes_redundancy_or_topology>",
      "repeatable_routine_task": "<repeatable_routine_task>"
    },
    "name": "classify_procedure"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_descriptionYes
has_back_out_planNo
approved_before_workNo
has_point_of_no_returnNo
repeatable_routine_taskYes
changes_redundancy_or_topologyYes
service_or_person_in_danger_nowYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the classification logic (danger-now stops at first safe state; MOP changes redundancy and needs PNoR/back-out/approval; SOP never changes redundancy) and the exclusion that a Permit to Work is not a fourth category. It does not state that the tool is a read-only analysis with no side effects, nor the precedence when several flags are true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in one sentence, followed by a compact three-line glossary plus one exclusion sentence. Every line carries decision-relevant information and there is no filler.

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 7-parameter tool with no annotations and no output schema, the definition covers the domain vocabulary and the meaning of the returned gap list. The one meaningful omission is precedence — what the tool returns when, for example, danger-now and redundancy-changing flags are both set.

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 compensate, and it largely does — the MOP definition maps to has_point_of_no_return, has_back_out_plan and approved_before_work, the EOP definition maps to service_or_person_in_danger_now, and the SOP definition maps to repeatable_routine_task and changes_redundancy_or_topology. What remains unstated is how these booleans combine or override one another when multiple are true.

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 opening sentence names a specific verb and resource ('Classify a data center task') and states the output ('list what the paper is missing'), then defines the three target classes. An agent can immediately tell this is a taxonomy/classification tool, distinct from siblings like classify_corrosion_coupon and liquid_loop_hydraulics.

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 description supplies decision criteria for choosing between EOP, MOP and SOP, which implicitly tells the agent when each label applies. However, it gives no guidance on when to call this tool versus other tools, and no statement of prerequisites or input expectations for the caller.

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