ThinkNEO Control Plane

thinkneo_sla_define

Idempotent

Define or update an SLA (Service Level Agreement) for an AI agent. Set accuracy, quality, cost, safety, or latency thresholds with automatic breach detection and configurable actions (alert, escalate, disable, switch_model). Like SRE SLOs but for AI agent outcomes. Requires authentication.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`metric`	Yes	Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)
`window`	No	Rolling window: '1h', '24h', '7d', or '30d'	7d
`threshold`	Yes	Target threshold value (e.g., 95.0 for 95% accuracy)
`agent_name`	Yes	Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')
`breach_action`	No	Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)	alert
`threshold_direction`	No	'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).	min

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedJun 26, 2026

changedInput schema / properties / agent_name / description

Previous value: -"Agent name"New value: +"Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')"

changedInput schema / properties / breach_action / description

Previous value: -"Action on breach: alert, escalate, disable, switch_model"New value: +"Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)"

changedInput schema / properties / metric / description

Previous value: -"Metric: accuracy, response_quality, cost_efficiency, safety, latency"New value: +"Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)"

changedInput schema / properties / threshold / description

Previous value: -"Target threshold value"New value: +"Target threshold value (e.g., 95.0 for 95% accuracy)"

addedInput schema / properties / threshold_direction

Added value: +{
+  "default": "min",
+  "description": "'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).",
+  "title": "Threshold Direction",
+  "type": "string"
+}

changedInput schema / properties / window / description

Previous value: -"Rolling window: 1h, 24h, 7d, 30d"New value: +"Rolling window: '1h', '24h', '7d', or '30d'"

Changed6 schema fields changedMay 11, 2026

changedInput schema / properties / agent_name / description

Previous value: -"Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')"New value: +"Agent name"

changedInput schema / properties / breach_action / description

Previous value: -"Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)"New value: +"Action on breach: alert, escalate, disable, switch_model"

changedInput schema / properties / metric / description

Previous value: -"Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)"New value: +"Metric: accuracy, response_quality, cost_efficiency, safety, latency"

changedInput schema / properties / threshold / description

Previous value: -"Target threshold value (e.g., 95.0 for 95% accuracy)"New value: +"Target threshold value"

removedInput schema / properties / threshold_direction

Removed value: -{
-  "default": "min",
-  "description": "'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).",
-  "title": "Threshold Direction",
-  "type": "string"
-}

changedInput schema / properties / window / description

Previous value: -"Rolling window: '1h', '24h', '7d', or '30d'"New value: +"Rolling window: 1h, 24h, 7d, 30d"

AddedApr 24, 2026

TDQS

A4/5.0

Behavior4/5

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

The annotations already establish this is a write operation (readOnlyHint false) that is idempotent and non-destructive. The description adds useful context by stating 'Requires authentication' and explaining that defining an SLA enables 'automatic breach detection and configurable actions,' which informs the agent of side effects. No contradictions with annotations.

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?

Four short sentences, each serving a purpose: definition, features, analogy, and auth requirement. The description is front-loaded with the primary action and remains free of 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 write tool with six parameters and an output schema, the description covers the core concept, metrics, actions, and authentication. The missing details (e.g., window and threshold_direction) are already documented in the schema, so the description does not need to repeat them. The lack of explicit prerequisites or return-value explanation is acceptable given the output schema.

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

Parameters3/5

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

The input schema provides 100% coverage with detailed descriptions for all six parameters, so the schema does the heavy lifting. The description reiterates the metric names and breach actions at a high level, which adds a small amount of interpretive context but no new syntax or format details 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 opens with a specific verb-resource pair: 'Define or update an SLA (Service Level Agreement) for an AI agent.' It then enumerates the metric types and configurable actions, making the tool's function clear. This distinguishes it from sibling tools like thinkneo_sla_status or thinkneo_sla_dashboard, which are about viewing SLA state.

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 implies the tool is for creating or updating SLA definitions, but it does not explicitly state when to use it versus alternatives such as thinkneo_alert_rule_create or the SLA status/breach tools. The SRE SLO analogy provides context but no exclusion criteria or alternatives are mentioned.

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

All ThinkNEO Control Plane tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.