Skip to main content
Glama
Sign In

Dagon Inference

by io.github.inkwell-finance
OverviewDiscussionsAdmin

Chat with a Dagon model

dagon_chat

Send a chat completion to a Dagon model (POST /v1/chat/completions, non-streaming) and return the reply with its signed receipt id. Spends credits of the connection's Authorization: Bearer key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model": "<model>"
    },
    "name": "dagon_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesModel id from dagon_models.
promptNoUser message. Use this or messages.
systemNoOptional system prompt, prepended to the conversation.
messagesNoFull conversation, OpenAI chat format. Use this or prompt.
max_tokensNo
temperatureNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so mutation/external-effect profile is partially covered. The description genuinely adds value by disclosing that it spends credits against the connection's Bearer key and that the reply carries a signed receipt id. It says nothing about failure modes, whether credits are spent on error, or rate limits, so it stops short of rich behavioral context.

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?

Two tight sentences with the action and endpoint front-loaded and cost/auth detail trailing. No filler, though the parenthetical endpoint notation could be dropped without loss.

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?

With no output schema, the description does state what comes back (reply plus signed receipt id), and it flags the credit cost of a write-effect call. The remaining gap is that temperature and max_tokens go unexplained anywhere, which matters for a generation tool.

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 67%, so the schema already explains model, prompt, system and messages, including the prompt-vs-messages either/or. The description adds nothing about temperature or max_tokens, the two parameters left undocumented in both places, so it does not compensate for the gap.

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 and resource -- 'Send a chat completion to a Dagon model' -- and pins down the endpoint and non-streaming mode. It is distinguishable from the account-management siblings (balance, keys, models) by content, though it never names an alternative tool.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance and no mention of an alternative for streaming or for listing models. The only implicit signal is 'non-streaming', which an agent must infer means this tool is not for streaming use.

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

All Dagon Inference toolsInspect
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