Skip to main content
Glama
Sign In
lightbulb-mcp

lightbulb-mcp

by RPasquale
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

evaluate_project_offline_policy

Estimate candidate policy performance from exact assignment/outcome pairs using deterministic IPS/SNIPS evaluation for offline comparison.

Instructions

Estimate a candidate from exact assignment/outcome receipt pairs.

Spring reconstructs every assignment, action event, outcome, metric, and project scope before deterministic IPS/SNIPS evaluation. Even a supported result remains a shadow candidate; it is not causal proof, learning admission, policy promotion/activation, or action authority.

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": {
      "project_id": "<project_id>",
      "behavior_policy_id": "<behavior_policy_id>",
      "candidate_policy_id": "<candidate_policy_id>",
      "metric_id": "<metric_id>",
      "pairs_json": "<pairs_json>"
    },
    "name": "evaluate_project_offline_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNo
metric_idYes
pairs_jsonYes
project_idYes
evaluation_idNo
confirm_evaluateNo
behavior_policy_idYes
candidate_policy_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

B3.3/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing that Spring reconstructs assignments, action events, outcomes, metrics, and project scope before deterministic evaluation, and that results are only 'shadow candidates' without causal or action authority. This is highly valuable behavioral context, especially since readOnlyHint is false and the tool may have side effects.

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 compact, front-loaded with the core purpose, and every sentence adds useful context. The second paragraph is dense but earns its place by clarifying the non-authoritative nature of the result.

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?

Given the tool's complexity, 8 parameters, and 0% schema description coverage, this description is incomplete for invocation. It provides strong caveats about result interpretation but lacks practical information about required inputs, how to construct pairs_json, and what confirm_evaluate does. The presence of an output schema helps, but invocation guidance is still insufficient.

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?

Schema description coverage is 0%, so the description carries the burden of explaining parameters, but it only indirectly touches on pairs_json ('exact assignment/outcome receipt pairs') and metric_id ('metric'). It does not explain behavior_policy_id, candidate_policy_id, confirm_evaluate, evaluation_id, or the structure/format of pairs_json.

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 states a specific verb ('estimate') and resource ('a candidate') and names the evaluation mechanism (IPS/SNIPS). It is not a tautology and the tool name plus 'offline policy' gives useful context, but 'a candidate' is slightly vague and could more explicitly say 'candidate policy performance'.

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?

There is no explicit guidance on when to use this tool versus alternatives, and no mention of excluded cases. The description implies it is for offline evaluation from exact assignment/outcome receipt pairs, but an agent is left to infer when this tool rather than a sibling evaluation/list tool is appropriate.

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

Deploy Server

Other Tools