Argus

Overview Schema Source Related Servers Discussions Admin

Finish Test and Write Reports

end_session

Destructive

Close an exploration session and export reports, optionally submitting final coverage updates atomically. Read unfinished goals and warnings—completion does not mean the application passed.

Instructions

Close and export reports. Optionally submit final coverage_updates (goal, exercised|blocked, evidence) atomically in this call. Invalid updates keep the session open. Read unfinished goals and warnings; completion is not an application pass.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "end_session"
  }
}

Input Schema

Name	Required	Description	Default
`coverage_updates`	No

Output Schema

Name	Required	Description	Default
`data`	No
`run_id`	Yes
`stages`	No
`status`	Yes
`recovery`	No
`operation`	Yes
`error_code`	Yes
`session_state`	Yes
`schema_version`	No
`progress_omitted`	No
`progress_delivery_failed`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.10.0Oct 26, 2026

addedInput schema / $defs

Added value: +{
+  "FinalCoverageUpdate": {
+    "properties": {
+      "evidence": {
+        "type": "string"
+      },
+      "goal": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "status": {
+        "enum": [
+          "exercised",
+          "blocked"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "goal",
+      "status",
+      "evidence"
+    ],
+    "type": "object"
+  }
+}

addedInput schema / properties / coverage_updates

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "$ref": "#/$defs/FinalCoverageUpdate"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

removedInput schema / title
```
Removed value: -"end_sessionArguments"
```

Changed12 schema fields changedOct 26, 2026
- removedOutput schema / properties / data / title
```
Removed value: -"Data"
```
- removedOutput schema / properties / error_code / title
```
Removed value: -"Error Code"
```
- removedOutput schema / properties / operation / title
```
Removed value: -"Operation"
```
- removedOutput schema / properties / progress_delivery_failed / title
```
Removed value: -"Progress Delivery Failed"
```
- removedOutput schema / properties / progress_omitted / title
```
Removed value: -"Progress Omitted"
```
- removedOutput schema / properties / recovery / title
```
Removed value: -"Recovery"
```
- removedOutput schema / properties / run_id / title
```
Removed value: -"Run Id"
```
- removedOutput schema / properties / schema_version / title
```
Removed value: -"Schema Version"
```
- removedOutput schema / properties / session_state / title
```
Removed value: -"Session State"
```
- removedOutput schema / properties / stages / title
```
Removed value: -"Stages"
```
- removedOutput schema / properties / status / title
```
Removed value: -"Status"
```
- removedOutput schema / title
```
Removed value: -"AgentResult"
```

Changed14 schema fields changedv0.5.2Oct 26, 2026

addedOutput schema / properties / data

Added value: +{
+  "additionalProperties": true,
+  "title": "Data",
+  "type": "object"
+}

addedOutput schema / properties / error_code

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "title": "Error Code"
+}

addedOutput schema / properties / operation

Added value: +{
+  "title": "Operation",
+  "type": "string"
+}

addedOutput schema / properties / progress_delivery_failed

Added value: +{
+  "default": false,
+  "title": "Progress Delivery Failed",
+  "type": "boolean"
+}

addedOutput schema / properties / progress_omitted

Added value: +{
+  "default": 0,
+  "title": "Progress Omitted",
+  "type": "integer"
+}

addedOutput schema / properties / recovery

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Recovery",
+  "type": "array"
+}

removedOutput schema / properties / result

Removed value: -{
-  "title": "Result",
-  "type": "string"
-}

addedOutput schema / properties / run_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "title": "Run Id"
+}

addedOutput schema / properties / schema_version

Added value: +{
+  "const": 1,
+  "default": 1,
+  "title": "Schema Version",
+  "type": "integer"
+}

addedOutput schema / properties / session_state

Added value: +{
+  "title": "Session State",
+  "type": "string"
+}

addedOutput schema / properties / stages

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Stages",
+  "type": "array"
+}

addedOutput schema / properties / status

Added value: +{
+  "enum": [
+    "completed",
+    "error"
+  ],
+  "title": "Status",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "operation",
+  "status",
+  "session_state",
+  "run_id",
+  "error_code"
+]

changedOutput schema / title

Previous value: -"end_sessionOutput"New value: +"AgentResult"

First observedv0.4.0Apr 27, 2026

TDQS

A4/5.0

Behavior4/5

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

Adds real information beyond the annotations: atomic submission of coverage_updates, the failure mode where 'invalid updates keep the session open', and the caveat that completion is not an application pass. It does not address the destructiveHint=true side — that the session is terminated and cannot be resumed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences, front-loaded with the primary action before the optional payload. Phrasing is telegraphic ('Read unfinished goals and warnings' lacks a subject) but no sentence is padding.

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?

An output schema exists, so return values need no explanation, and the description covers the main behavioral risks of atomic failure. The remaining gap is the irreversible teardown implied by destructiveHint=true, which is never stated.

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

Parameters4/5

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

With 0% schema description coverage, the description carries the burden and does meaningful work: it enumerates the nested fields (goal, status, evidence) and the exercised|blocked enum. It omits that `goal` accepts a string or array and says nothing about the shape of `evidence`.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource pair ('Close and export reports') and implies the terminal counterpart to start_session. The nature of the 'reports' is left vague, but the operation is unmistakable against siblings like coverage_update or record_bug.

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?

Clearly positions itself as the end-of-session call and distinguishes its optional payload as 'final' coverage updates, implicitly contrasting with the incremental coverage_update sibling. No explicit exclusions or preconditions (e.g., must a session be active?) are given.

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