check_agent_qualityAnalyze supplied agent traces. Free, read-only calculation. Requires an active agent key; does not change agents or initiate payments.
| Name | Required | Description | Default |
|---|---|---|---|
| runs | Yes | ||
| config | No |
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | ||
| workflows | Yes | ||
| schema_version | Yes |
Changes observed during successful MCP inspections.
Input schema / descriptionAdded value: +"Recorded attempts, not prompts or secrets. Identical rows count as separate attempts. All three analysis tools accept this same input. The runtime validator additionally enforces six-decimal micro-USD precision, the same task_id belonging to one workflow, one workflow when monthlyTasks is given, and UTF-16 length limits. HTTP body limit: 512000 UTF-8 bytes."Input schema / properties / config / additionalPropertiesAdded value: +falseInput schema / properties / config / propertiesAdded value: +{
+ "maxP95LatencyMs": {
+ "maximum": 86400000000,
+ "minimum": 0,
+ "type": "number"
+ },
+ "maxSuccessRateDrop": {
+ "default": 0.02,
+ "maximum": 1,
+ "minimum": 0,
+ "type": "number"
+ },
+ "minSamples": {
+ "default": 30,
+ "maximum": 500,
+ "minimum": 2,
+ "type": "integer"
+ },
+ "minSuccessRate": {
+ "default": 0.95,
+ "maximum": 1,
+ "minimum": 0,
+ "type": "number"
+ },
+ "monthlyTasks": {
+ "description": "Baseline logical tasks launched per month; the engine requires exactly one workflow if supplied.",
+ "maximum": 1000000,
+ "minimum": 1,
+ "type": "integer"
+ }
+}Input schema / properties / config / requiredAdded value: +[]Input schema / properties / runs / items / additionalPropertiesAdded value: +falseInput schema / properties / runs / items / propertiesAdded value: +{
+ "cost_usd": {
+ "description": "USD cost of this attempt. At most six decimal places; the engine verifies whole micro-USD using floating-point tolerance. No multipleOf keyword is used, to avoid rejecting valid JSON decimals.",
+ "maximum": 10000,
+ "minimum": 0,
+ "type": "number"
+ },
+ "latency_ms": {
+ "description": "Recorded attempt duration in milliseconds; decimals are accepted. Omit if not measured.",
+ "maximum": 86400000,
+ "minimum": 0,
+ "type": "number"
+ },
+ "success": {
+ "type": "boolean"
+ },
+ "task_id": {
+ "description": "Nonempty, no control characters or surrounding whitespace. The engine additionally enforces at most 128 UTF-16 code units.",
+ "maxLength": 128,
+ "minLength": 1,
+ "pattern": "^(?!\\s)(?![\\s\\S]*\\s$)[^\\u0000-\\u001F\\u007F]+$",
+ "type": "string"
+ },
+ "variant": {
+ "enum": [
+ "baseline",
+ "candidate"
+ ],
+ "type": "string"
+ },
+ "workflow": {
+ "description": "Nonempty, no control characters or surrounding whitespace. The engine additionally enforces at most 80 UTF-16 code units.",
+ "maxLength": 80,
+ "minLength": 1,
+ "pattern": "^(?!\\s)(?![\\s\\S]*\\s$)[^\\u0000-\\u001F\\u007F]+$",
+ "type": "string"
+ }
+}Input schema / properties / runs / items / requiredAdded value: +[
+ "task_id",
+ "workflow",
+ "variant",
+ "cost_usd",
+ "success"
+]Input schema / titleAdded value: +"ALPNAI recorded agent attempts"Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "config": {
+ "additionalProperties": true,
+ "properties": {
+ "maxP95LatencyMs": {
+ "maximum": 86400000000,
+ "minimum": 0,
+ "type": "number"
+ },
+ "maxSuccessRateDrop": {
+ "default": 0.02,
+ "maximum": 1,
+ "minimum": 0,
+ "type": "number"
+ },
+ "minSamples": {
+ "default": 30,
+ "maximum": 500,
+ "minimum": 2,
+ "type": "integer"
+ },
+ "minSuccessRate": {
+ "default": 0.95,
+ "maximum": 1,
+ "minimum": 0,
+ "type": "number"
+ },
+ "monthlyTasks": {
+ "description": "Baseline logical tasks launched per month; the engine requires exactly one workflow if supplied.",
+ "maximum": 1000000,
+ "minimum": 1,
+ "type": "integer"
+ }
+ },
+ "required": [
+ "minSamples",
+ "minSuccessRate",
+ "maxSuccessRateDrop"
+ ],
+ "type": "object"
+ },
+ "schema_version": {
+ "const": "1.0.0",
+ "type": "string"
+ },
+ "workflows": {
+ "items": {
+ "additionalProperties": true,
+ "properties": {
+ "automatic_deployment_authorized": {
+ "const": false,
+ "type": "boolean"
+ },
+ "baseline_success": {
+ "anyOf": [
+ {
+ "maximum": 1,
+ "minimum": 0,
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "candidate_success": {
+ "anyOf": [
+ {
+ "maximum": 1,
+ "minimum": 0,
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "comparison": {
+ "additionalProperties": true,
+ "properties": {
+ "baseline_only_tasks": {
+ "maximum": 1000,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "candidate_only_tasks": {
+ "maximum": 1000,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "matched_task_ids": {
+ "maximum": 1000,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "same_task_set": {
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "matched_task_ids",
+ "baseline_only_tasks",
+ "candidate_only_tasks",
+ "same_task_set"
+ ],
+ "type": "object"
+ },
+ "decision": {
+ "enum": [
+ "missing_comparison",
+ "collect_more_data",
+ "quality_regression",
+ "latency_data_required",
+ "latency_regression",
+ "no_economic_advantage",
+ "candidate_for_controlled_trial"
+ ],
+ "type": "string"
+ },
+ "gates": {
+ "additionalProperties": true,
+ "properties": {
+ "both_variants": {
+ "enum": [
+ "pass",
+ "fail",
+ "unknown",
+ "not_requested"
+ ],
+ "type": "string"
+ },
+ "experimental_bias_control": {
+ "const": "unknown",
+ "type": "string"
+ },
+ "lower_cost_per_successful_task": {
+ "enum": [
+ "pass",
+ "fail",
+ "unknown",
+ "not_requested"
+ ],
+ "type": "string"
+ },
+ "minimum_distinct_tasks_per_variant": {
+ "enum": [
+ "pass",
+ "fail",
+ "unknown",
+ "not_requested"
+ ],
+ "type": "string"
+ },
+ "observed_success_rate": {
+ "enum": [
+ "pass",
+ "fail",
+ "unknown",
+ "not_requested"
+ ],
+ "type": "string"
+ },
+ "recorded_latency": {
+ "enum": [
+ "pass",
+ "fail",
+ "unknown",
+ "not_requested"
+ ],
+ "type": "string"
+ },
+ "same_task_set": {
+ "enum": [
+ "pass",
+ "fail",
+ "unknown",
+ "not_requested"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "both_variants",
+ "minimum_distinct_tasks_per_variant",
+ "same_task_set",
+ "observed_success_rate",
+ "recorded_latency",
+ "lower_cost_per_successful_task",
+ "experimental_bias_control"
+ ],
+ "type": "object"
+ },
+ "workflow": {
+ "description": "Nonempty, no control characters or surrounding whitespace. The engine additionally enforces at most 80 UTF-16 code units.",
+ "maxLength": 80,
+ "minLength": 1,
+ "pattern": "^(?!\\s)(?![\\s\\S]*\\s$)[^\\u0000-\\u001F\\u007F]+$",
+ "type": "string"
+ }
+ },
+ "required": [
+ "workflow",
+ "comparison",
+ "gates",
+ "decision",
+ "baseline_success",
+ "candidate_success",
+ "automatic_deployment_authorized"
+ ],
+ "type": "object"
+ },
+ "maxItems": 1000,
+ "minItems": 1,
+ "type": "array"
+ }
+ },
+ "required": [
+ "schema_version",
+ "config",
+ "workflows"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds concrete behavioral context beyond the annotations: the authentication requirement ('active agent key') and financial neutrality ('does not initiate payments'). It also explicitly states 'does not change agents,' reinforcing the readOnlyHint and destructiveHint annotations. No contradictions with the annotation set.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense sentence conveys the action, scope, cost, and side-effect profile. Every clause earns its place, and the most important facts are front-loaded. There is no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description, together with a detailed input schema and an output schema, covers the essential call context: what input to provide, what operation is performed, the key requirement, and the absence of side effects. Minor gap: it does not explain what 'quality' means or how thresholds in config affect the result, but the schema and output schema largely cover those details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no parameter-level information at all; schema_description_coverage is 0%. It does not mention runs or config, so it fails to compensate for the low coverage. The input schema itself is well-documented, but the tool description adds zero parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Analyze supplied agent traces.' The title 'Quality Gate' reinforces the tool's purpose. It distinguishes itself from the purchase_* siblings via 'Free, read-only calculation' and 'does not initiate payments,' though it does not explicitly differentiate from the other analysis sibling tools like analyze_agent_latency.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context is provided: free, read-only, requires an active agent key, and no side effects. This implies use when a no-cost quality assessment is needed without triggering payments. However, it does not explicitly name alternatives or state when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.