Repo Test Architect

Overview Schema Source Related Servers Discussions Admin

Generate Test Plan

generate_test_plan

Read-onlyIdempotent

Create a deterministic plan/v1 from an existing single-project audit/v1 artifact; optionally return one item. Does not rescan, run tests, or write code.

Instructions

Create a deterministic plan/v1 from an existing single-project audit/v1 artifact. Use this after audit_repo, optionally selecting one exact plan item; use generate_project_test_plan for multiple audited projects. Does not rescan the repository, execute tests, or generate or write test code.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`audit`	Yes	The audit/v1 object returned by audit_repo or contained in projectAudits.audits[].audit; pass the artifact itself, not a file path.
`itemId`	No	Optional exact plan item id to return; omit it to return the complete deterministic plan.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`items`	Yes
`summary`	Yes
`blockers`	Yes
`schemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.0.0Oct 2, 2026

changedInput schema / properties / audit / description

Previous value: -"An audit/v1 artifact."New value: +"The audit/v1 object returned by audit_repo or contained in projectAudits.audits[].audit; pass the artifact itself, not a file path."

changedInput schema / properties / itemId / description

Previous value: -"Optional stable plan item id to select."New value: +"Optional exact plan item id to return; omit it to return the complete deterministic plan."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$id": "https://repo-test-architect.local/schemas/plan-v1.schema.json",
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "blockers": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "items": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "action": {
+            "enum": [
+              "add-test",
+              "extend-test",
+              "defer"
+            ]
+          },
+          "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"
+          },
+          "id": {
+            "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"
+          },
+          "sourceSignals": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "target": {
+            "type": "string"
+          },
+          "targetId": {
+            "type": "string"
+          },
+          "testLevel": {
+            "enum": [
+              "unit",
+              "integration",
+              "component",
+              "ui",
+              "none"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "action",
+          "targetId",
+          "target",
+          "path",
+          "testLevel",
+          "priority",
+          "riskReductionScore",
+          "maintenanceCost",
+          "rationale",
+          "sourceSignals",
+          "existingTestPaths"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "schemaVersion": {
+      "const": "plan/v1"
+    },
+    "summary": {
+      "additionalProperties": false,
+      "properties": {
+        "addTestCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "blockerCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "confidence": {
+          "enum": [
+            "low",
+            "medium",
+            "high"
+          ]
+        },
+        "deferredCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "extendTestCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "verificationCommand": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "confidence",
+        "blockerCount",
+        "addTestCount",
+        "extendTestCount",
+        "deferredCount"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "schemaVersion",
+    "summary",
+    "blockers",
+    "items"
+  ],
+  "title": "Repo Test Architect Test Plan",
+  "type": "object"
+}

First observedv0.1.0Aug 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so safety is covered structurally. The description adds genuinely useful negative scope: it does not rescan the repository, does not execute tests, and does not generate or write test code. It could go further on what 'deterministic' guarantees or on failure if the audit is invalid, but the boundary-setting is strong.

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?

Three tight sentences: purpose first, then prerequisites and disambiguation, then explicit non-capabilities. Every sentence carries load and nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the description covers source artifact, sequencing, alternative, and exclusions. For a read-only two-parameter tool with fully covered schema, this is complete.

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?

Schema coverage is 100%, and the schema already documents both 'audit' (pass the object, not a path) and 'itemId' (exact plan item, omit for full plan). The description only echoes the itemId behavior ('optionally selecting one exact plan item') without adding syntax, format, or id-source detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ('Create a deterministic plan/v1') plus the exact source artifact type ('existing single-project audit/v1 artifact'). It explicitly names the multi-project sibling generate_project_test_plan, so an agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

'Use this after audit_repo, optionally selecting one exact plan item' gives the prerequisite and the optional narrowing condition, and 'use generate_project_test_plan for multiple audited projects' states the exclusion and alternative. Nothing is left to inference.

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