VibeRaven

Check recent provider changes

recent_provider_changes

Read-onlyIdempotent

recent_provider_changes({"provider":"supabase","query":"42501","limit":5}) Use when a provider update may explain changed behavior, or a deployment needs review against dated provider changes. Returns candidate changes, documented errors or symptoms, fixes, date meanings and official supporting sources. Filter by provider or redacted error keywords. For general troubleshooting use search_guides; for setup use provider_playbook. Available providers: anthropic, clerk, lovable, nextjs, openai, railway, stripe, supabase, vercel. Limits: guidance only; does not read your repo, connect to providers, run fixes or verify rollout, deployment or live behavior.

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": "recent_provider_changes"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum entries, 1 to 8; default 5.
`query`	No	Optional redacted error text or public keywords. Remove credentials, private paths and personal data before calling.
`provider`	No	Optional lowercase provider id. Unsupported ids return the bounded available list.

Output Schema

Name	Required	Description	Default
`limits`	Yes
`entries`	Yes
`nextStep`	No
`packHash`	Yes
`reviewedAt`	Yes
`packVersion`	Yes
`verification`	Yes
`dateConvention`	Yes
`availableProviders`	Yes
`correctionsAndConflicts`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026
- addedOutput schema / properties / nextStep / properties / codingAgentTask
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "clerk",
-  "lovable",
-  "nextjs",
-  "railway",
-  "supabase",
-  "vercel"
-]New value: +[
+  "anthropic",
+  "clerk",
+  "lovable",
+  "nextjs",
+  "openai",
+  "railway",
+  "stripe",
+  "supabase",
+  "vercel"
+]

Changed1 schema field changedOct 31, 2026

addedOutput schema / properties / nextStep

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "label": {
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "label",
+    "url"
+  ],
+  "type": "object"
+}

AddedOct 30, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the bar is lower, yet the description still adds meaningful behavioral context: it is guidance-only, cannot read the caller's repo or connect to providers, and returns dated evidence rather than live verification. It does not discuss result volume beyond the limit parameter, so it stops short of a fully rounded behavioural picture.

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?

The opening example call front-loads intent efficiently and the when-to-use, alternatives, and limits sentences each earn their place. Minor waste comes from restating the provider list and the filter fields already present in the schema.

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 and full schema coverage, the description only needs to cover intent, routing, and boundaries, all of which it does. An agent knows what it returns, when to pick it, when to pick a sibling, and what it must not expect it to do.

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 description coverage is 100%, including the enum and the redaction warning, so the schema already carries the parameter burden. The description only echoes that filtering is possible by provider or redacted error keywords and repeats the provider list that is already an enum, adding no new semantics such as query matching behavior or ranking.

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 description states exactly what the tool surfaces (candidate provider changes, documented errors/symptoms, fixes, date meanings, official sources) and scopes it to a dated provider-change resource. It also names the two siblings it is not (search_guides for general troubleshooting, provider_playbook for setup), so an agent can separate it from alternatives without reading any 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?

It gives an explicit trigger ('when a provider update may explain changed behavior, or a deployment needs review against dated provider changes') plus clear routing rules to search_guides and provider_playbook. The 'Limits' sentence adds explicit when-not boundaries by ruling out repo inspection, provider connection, running fixes, and rollout verification.

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

All VibeRaven tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.