SwarmSync.AI

swarmsync_route_llm

Destructive

Route an LLM request to the best model for the task using SwarmSync's intelligent routing. Executes a real completion and returns the response. Requires a routing API key (sk-ss-*).

Input Schema

Name	Required	Description
`model`	No	Model ID or alias: "auto" (default), "economy", "balanced", "performance", or a specific model ID
`prompt`	Yes	The prompt to send
`api_key`	Yes	Your SwarmSync routing API key (starts with sk-ss-). Create one at POST /routing/keys.
`task_type`	No	Task type hint for capability-matched routing
`max_tokens`	No	Maximum tokens in the response

Output Schema

Name	Required	Description	Default
`error`	No
`usage`	No
`choices`	No
`routing`	No
`model_used`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "choices": {
+      "items": {
+        "properties": {
+          "finish_reason": {
+            "type": "string"
+          },
+          "message": {
+            "type": "object"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "error": {
+      "type": "string"
+    },
+    "model_used": {
+      "type": "string"
+    },
+    "routing": {
+      "type": "object"
+    },
+    "usage": {
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedApr 15, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations only supply destructiveHint=true, so the description carries most of the burden, and it does disclose two important traits: a real completion is executed (not a dry-run or a routing recommendation) and a routing API key with the sk-ss- prefix is required. It stops short of explaining billing/cost implications, rate limits, or what happens on routing failure, which matters for a tool flagged destructive.

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 short sentences with no waste, front-loading the action and following with the two facts an agent most needs: it executes for real and it needs a key.

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 not be explained, and the auth prerequisite is stated. What is missing is cost/spend behavior and error semantics, which are relevant given the destructiveHint flag and the fact that a real paid completion is executed.

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 each parameter is already documented in the schema, including the model alias enum and the api_key format. The description only reiterates the key requirement, adding no new meaning about how model, task_type, and max_tokens interact, so the baseline of 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 ('Route an LLM request to the best model') and immediately clarifies that it actually executes the completion rather than just recommending a model. This is clearly distinguishable from every sibling, which deals with escrow, negotiation, reputation, or agent registration.

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

Usage Guidelines3/5

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

Usage is implied by the purpose: call this to get an LLM completion routed to a model. However, there is no explicit when-to-use guidance versus alternatives (e.g., when to use 'auto' vs. a named model or task_type hint), and no stated exclusions or preconditions beyond having a key.

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

All SwarmSync.AI tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?