canli-mcp / The desk, built into canli-mcp

What a tool cost earlier in this session

Before a heavy call: how long the tool took and how many characters it answered with when it ran earlier in this session (median and largest), and whether it reads the network, so a call can set max_chars or select first.

The tool is cost_preview in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It is part of canli-mcp itself, so it is there as soon as canli-mcp is added.

Arguments

As the server declares them
ArgumentRequiredType
nameyesstring

How a model reaches it

Ask in plain words. The model finds cost_preview with canli-mcp's find_tool, reads its arguments with describe_tool if it needs to, and runs it with run_tool. The call has this shape, with your values in place of the angle brackets:

{
  "name": "cost_preview",
  "arguments": {
    "name": "<string>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to cost_preview on these words: cost, preview, estimate, how, long, big, tokens, size, before, calling, heavy, expensive, tool, budget.

More

Nothing here is investment advice.