rank_test_candidatesRanks testable audit targets by risk reduction and maintenance cost, helping teams decide which repository areas to test first.
Rank testable audit targets by risk reduction and maintenance cost.
| Name | Required | Description | Default |
|---|---|---|---|
| audit | Yes | An audit/v1 artifact. |
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes | ||
| blockers | Yes | ||
| candidates | Yes | ||
| schemaVersion | Yes |
Changes observed during successful MCP inspections.
v1.0.0Output schema / (root)Previous value: -nullNew value: +{
+ "$id": "https://repo-test-architect.local/schemas/candidate-ranking-v1.schema.json",
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "blockers": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "candidates": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "enum": [
+ "untested",
+ "covered-but-risky"
+ ]
+ },
+ "existingTestEvidence": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "kind": {
+ "type": "string"
+ },
+ "strength": {
+ "enum": [
+ "naming",
+ "direct",
+ "referenced",
+ "indirect"
+ ]
+ },
+ "testPath": {
+ "type": "string"
+ },
+ "usage": {
+ "enum": [
+ "called",
+ "asserted"
+ ]
+ },
+ "viaUsage": {
+ "enum": [
+ "called",
+ "asserted"
+ ]
+ }
+ },
+ "required": [
+ "testPath",
+ "kind",
+ "strength"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "existingTestPaths": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "kind": {
+ "type": "string"
+ },
+ "maintenanceCost": {
+ "maximum": 10,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "path": {
+ "type": "string"
+ },
+ "priority": {
+ "type": "integer"
+ },
+ "rationale": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "riskReductionScore": {
+ "maximum": 10,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "signals": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "target": {
+ "type": "string"
+ },
+ "targetId": {
+ "type": "string"
+ },
+ "testLevel": {
+ "enum": [
+ "unit",
+ "integration",
+ "component",
+ "ui",
+ "none"
+ ]
+ }
+ },
+ "required": [
+ "targetId",
+ "target",
+ "path",
+ "category",
+ "kind",
+ "testLevel",
+ "priority",
+ "riskReductionScore",
+ "maintenanceCost",
+ "signals",
+ "rationale",
+ "existingTestPaths"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "schemaVersion": {
+ "const": "candidate-ranking/v1"
+ },
+ "summary": {
+ "additionalProperties": false,
+ "properties": {
+ "blockerCount": {
+ "minimum": 0,
+ "type": "integer"
+ },
+ "candidateCount": {
+ "minimum": 0,
+ "type": "integer"
+ },
+ "confidence": {
+ "enum": [
+ "low",
+ "medium",
+ "high"
+ ]
+ },
+ "verificationCommand": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "confidence",
+ "candidateCount",
+ "blockerCount"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "schemaVersion",
+ "summary",
+ "blockers",
+ "candidates"
+ ],
+ "title": "Repo Test Architect Candidate Ranking",
+ "type": "object"
+}v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive). The description adds the ranking criteria (risk reduction, maintenance cost), which is useful behavioral context beyond annotations, but does not disclose output format, required audit structure, or other operational details.
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, front-loaded sentence with no wasted words. It directly conveys the tool's core action and ranking basis.
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?
With annotations covering safety, a 100%-covered input schema, and an output schema that explains return values, the description is nearly complete for this tool. The only gap is the absence of usage guidance relative to siblings like rank_project_candidates.
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?
Schema description coverage is 100%, so the single parameter 'audit' is fully documented in the schema. The description adds no parameter-specific information, which is acceptable given the high coverage baseline.
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?
States a specific verb ('Rank') and resource ('testable audit targets') with ranking criteria ('risk reduction and maintenance cost'). Implicitly distinguishes from rank_project_candidates by focusing on audit targets rather than project candidates, but does not name the sibling explicitly.
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?
No guidance on when to use this tool versus alternatives. The description only states what it does, not when it is appropriate or what prerequisites exist, leaving the agent to infer from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.