List the models this gateway can route to, best first. Every one is reachable with the same Qumge key — no per-vendor signup. Only tool-calling models are listed: an agent cannot use the others.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many to return. Default 20, max 60. | |
| query | No | Optional. Filter by name or vendor, e.g. 'claude', 'gemini'. |
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| total | Yes | ||
| models | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / qumge_keyRemoved value: -{
- "description": "Optional: your Qumge API key, for clients that cannot set an Authorization header. Takes precedence over the header. Never echoed back.",
- "type": "string"
-}Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "limit": {
+ "type": "integer"
+ },
+ "models": {
+ "items": {
+ "properties": {
+ "id": {
+ "type": "string"
+ },
+ "input_price_per_mtok_usd": {
+ "type": "number"
+ },
+ "name": {
+ "type": "string"
+ },
+ "output_price_per_mtok_usd": {
+ "type": "number"
+ },
+ "provider": {
+ "type": "string"
+ },
+ "slug": {
+ "type": "string"
+ },
+ "vision": {
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "id",
+ "provider",
+ "slug",
+ "name"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "total": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "models",
+ "total"
+ ],
+ "type": "object"
+}Input schema / properties / qumge_keyAdded value: +{
+ "description": "Optional: your Qumge API key, for clients that cannot set an Authorization header. Takes precedence over the header. Never echoed back.",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers real operational context: a single Qumge key covers every vendor with no per-vendor signup, and non-tool-calling models are excluded ('an agent cannot use the others'). It does not mention pagination limits (left to the schema) or error behavior, so it falls short of exhaustive.
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?
Three tight sentences, front-loaded with the action and ordering before the two caveats. Every sentence carries information an agent cannot get from the schema.
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?
An output schema exists, so return values need not be described, and parameters are fully covered by the schema. The description supplies the essential caveats (tool-calling-only, unified key, best-first ordering); only explicit usage guidance is absent.
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 both parameters (limit, query) are already fully documented. The description only obliquely relates to ordering via 'best first' and adds no syntax or semantics for the parameters beyond the schema. Baseline 3 applies.
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 and resource ('List the models this gateway can route to') plus meaningful scope constraints: ordering ('best first') and eligibility ('Only tool-calling models'). The sibling set (caps, skills, domains, payouts) is unrelated, so no differentiation is needed.
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?
Usage is implied – call it to discover routable models – but there is no explicit when-to-use, when-not-to-use, or named alternative. Since no sibling overlaps in function, the omission is low-risk rather than misleading.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.