Skip to main content
Glama
juyterman1000

entroly-context-engine

by juyterman1000
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

manage_skills

List, benchmark, validate, and promote skills based on evidence from held-out validation cases to ensure only validated skills advance.

Instructions

Manage the CogOps skill lifecycle (Evolution layer).

Actions:

  • list: Show effective status after promotion-evidence validation

  • benchmark: Run development cases (not sufficient for promotion)

  • validate: Run caller-held-out cases supplied in validation_cases_json

  • promote: Apply the latest caller-held-out evidence decision

Args: action: list | benchmark | validate | promote skill_id: Required for benchmark/validate/promote actions validation_cases_json: JSON array of independent cases for validate

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionNolist
skill_idNo
validation_cases_jsonNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.64
    • addedInput schema / properties / validation_cases_json
      Added value: +{
+  "default": "",
+  "title": "Validation Cases Json",
+  "type": "string"
+}
  2. Addedv1.0.55
  3. Removedv1.0.54
  4. First observedv1.0.42

TDQS

A4.3/5.0
Behavior3/5

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

With no annotations, the description carries the behavioral disclosure burden. It does disclose important semantic distinctions such as benchmark not being sufficient for promotion and validate requiring caller-held-out cases. However, it does not mention permissions, side effects of promote, reversibility, or error/response behavior, leaving meaningful gaps.

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 description is well-structured with Actions and Args bullets, front-loads the lifecycle context, and contains no filler. Every line conveys useful 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?

Given the tool's four-mode complexity and absent annotations, the description covers action semantics and parameter requirements sufficiently for invocationches, and an output schema exists so return values need not be described. It could still explain promotion-evidence validation and success/error responses more explicitly, preventing a 5.

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

Parameters5/5

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

The schema has 0% description coverage and no enums, so the Args section fully compensates. It defines allowed action values, conditionally required skill_id per action, and the JSON array format for validation_cases_json, adding essential meaning beyond the schema.

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 the tool manages the CogOps skill lifecycle and enumerates four concrete actions with specific outcomes. This distinguishes it from sibling tools like create_skill or record_outcome, even without naming them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

Each action is tied to a clear usage context: benchmark is explicitly 'not sufficient for promotion', validate is scoped to caller-held-out cases, and promote applies the latest decision. It lacks explicit comparison to alternative sibling tools, but the action-level guidance is strong.

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