wals.pro AI 4 weclapp

Preview support escalation

preview_escalate_to_support

Read-onlyIdempotent

Preview a customer-confirmed platform or partner ticket and issue an approval token.

when_to_use: Support or feature wishes (offer proactively). Show the full preview and resolved support destination; get explicit consent first. Ask for missing facts; never invent. Tried steps are required, never optional. Use informal du in German. Own words only: no copied chat text, personal data or credentials. Server redaction applies; preview shows exactly what is sent. kind="chat_review": this assistant's own behaviour, reviewed by the weclapp-mcp team; only description (summary, max 500), category, contact_email, chat_review. Args: kind: support (default) | chat_review. title: Max 120 chars. description: Expected vs. actual; support ≤2000 chars. category: support bug|feature_gap|how_to|data_issue|other; chat_review bug|hallucination|tool_misuse|safety|other. responsible_person: Case owner. contact_email: Problem contact (replies: verified contact). occurred_at: ISO 8601 as stated; never invented. steps_already_tried: 1–10 concrete attempts. example_records: Max 10 {entity_name, entity_id, note}. weclapp_url: https link on this workspace's host. hypotheses: Max 5 causes. problem_scope: platform | customer_erp | unclear; recommend, customer decides. support_target: platform | partner; resolved server-side, no free destination. chat_review: {tool_calls_of_interest?}, max 10 {tool, note}. preconditions: support needs title, responsible_person, contact_email, occurred_at, steps_already_tried. Max 10 per day. post_effects: Token only; after the user explicitly confirms: execute_approved(approval.token, execution.payload).

Input Schema

TableJSON Schema

Name	Required	Default
`kind`	No	support
`title`	No
`category`	Yes
`hypotheses`	No
`chat_review`	No
`description`	Yes
`occurred_at`	No
`weclapp_url`	No
`contact_email`	No
`problem_scope`	No
`correlation_id`	No
`support_target`	No
`example_records`	No
`responsible_person`	No
`steps_already_tried`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 4, 2026

addedInput schema / properties / problem_scope

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "platform",
+        "customer_erp",
+        "unclear"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Problem Scope"
+}

addedInput schema / properties / support_target

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "platform",
+        "partner"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Support Target"
+}

Changed20 schema fields changedSep 27, 2026

changedInput schema / properties / category / enum

Previous value: -[
-  "bug",
-  "feature_gap",
-  "how_to",
-  "data_issue",
-  "other"
-]New value: +[
+  "bug",
+  "feature_gap",
+  "how_to",
+  "data_issue",
+  "other",
+  "hallucination",
+  "tool_misuse",
+  "safety"
+]

addedInput schema / properties / chat_review

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Chat Review"
+}

addedInput schema / properties / contact_email / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / contact_email / default
```
Added value: +null
```
removedInput schema / properties / contact_email / type
```
Removed value: -"string"
```

addedInput schema / properties / kind

Added value: +{
+  "default": "support",
+  "enum": [
+    "support",
+    "chat_review"
+  ],
+  "title": "Kind",
+  "type": "string"
+}

addedInput schema / properties / occurred_at / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / occurred_at / default
```
Added value: +null
```
removedInput schema / properties / occurred_at / type
```
Removed value: -"string"
```

addedInput schema / properties / responsible_person / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / responsible_person / default
```
Added value: +null
```
removedInput schema / properties / responsible_person / type
```
Removed value: -"string"
```

addedInput schema / properties / steps_already_tried / anyOf

Added value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / steps_already_tried / default
```
Added value: +null
```
removedInput schema / properties / steps_already_tried / items
```
Removed value: -{
-  "type": "string"
-}
```
removedInput schema / properties / steps_already_tried / type
```
Removed value: -"array"
```

addedInput schema / properties / title / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / title / default
```
Added value: +null
```
removedInput schema / properties / title / type
```
Removed value: -"string"
```

changedInput schema / required

Previous value: -[
-  "title",
-  "description",
-  "category",
-  "responsible_person",
-  "contact_email",
-  "occurred_at",
-  "steps_already_tried"
-]New value: +[
+  "description",
+  "category"
+]

First observedSep 25, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true and non-destructive/idempotent, but the description adds what annotations cannot: server redaction applies, preview equals exactly what is sent, a hard rate limit (max 10/day), a 'never invent' fact policy, and a post-effect that is only a token requiring explicit user confirmation. This is unusually rich behavioral disclosure.

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?

Front-loaded with the core action, then sectioned into when_to_use / Args / preconditions / post_effects. Dense but every line is operative for a 15-parameter, consent-gated tool; no filler.

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?

For a 15-param, open-world escalation tool with an output schema present, the description supplies the missing schema docs, the consent workflow, the rate limit, and the token/execute handoff. An agent has everything needed to call it correctly and safely.

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

Parameters5/5

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

Schema coverage is 0%, so the description carries the full burden, and it does: max lengths (title 120, description 2000, summary 500), per-kind category enums, ISO 8601 with 'never invented', 1–10 steps_already_tried, max 10 example_records, max 5 hypotheses, host-constrained weclapp_url, and server-resolved support_target. Only correlation_id goes undocumented, which is a minor omission against otherwise exhaustive coverage.

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 first sentence gives a precise verb+resource+output: 'Preview a customer-confirmed platform or partner ticket and issue an approval token.' It is immediately distinguishable from sibling previewers (preview_write_entity, preview_stock_operation) and from execute_approved, which it names as the follow-up step.

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?

Explicit when_to_use (support or feature wishes, offer proactively), explicit consent requirement ('show the full preview... get explicit consent first'), explicit preconditions, and an explicit next action (execute_approved(approval.token, execution.payload) after user confirmation). 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.

All wals.pro AI 4 weclapp 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.

Resources

Need Help?