# Getting started

What Forecall measures, what you can do for free, including the Failure KB for your agents, what the paid plans add, and what static scoring cannot tell.

An AI agent chooses a tool by reading its name, its description and its input schema. When the
text is vague, the agent picks the wrong tool, fills in the wrong arguments, or never calls the
tool at all. Forecall measures how well your MCP tools are written for that reader, and shows you
what to fix.

## What Forecall measures

Forecall reads what your MCP server returns for `tools/list` and scores each tool out of 100 on
six things a model needs to choose and call it:

- its purpose
- when to use it, and when not to
- its arguments
- its return value
- its constraints and side effects
- examples

It also looks across the whole server: too many tools, tools that are easy to mix up, and tools
that share the same description. Each finding comes with an issue code and a severity (critical,
major or minor), so you can fix the worst first. [Read your scores](https://forecall.dev/en/docs/reading-scores) goes
through the items and every issue code.

This is static scoring: Forecall reads the text and never runs your server or a model. Measuring
how often real models choose and call your tools correctly is the job of
[evaluations](https://forecall.dev/en/docs/evaluations).

## Free and paid

Free, with no sign-up:

- **The linter on the web**: paste your `tools/list` JSON at [the linter](https://forecall.dev/en/lint). You get a
  result page whose URL you can share. Anyone with the URL can see it, search engines do not list
  it, and it is deleted after 30 days.
- **[The CLI](https://forecall.dev/en/docs/cli)**: `npx forecall lint tools.json` scores a file on your own machine
  with the same rules and sends nothing anywhere. Use it in CI to keep scores from dropping.

Free, with an account at [app.forecall.dev](https://app.forecall.dev):

- **[Servers and history](https://forecall.dev/en/docs/dashboard)**: register your servers and follow their scores
  over time.
- **[API keys](https://forecall.dev/en/docs/api)**: score from your own scripts and CI through the REST API, within a
  small monthly allowance.
- **[The Failure KB](https://forecall.dev/en/docs/kb)**: connect your AI agent with `npx forecall setup`, so that it
  looks up known failures of MCP tools and their workarounds before and after a call, within a
  monthly allowance of lookups.

Paid, on the Pro and Team plans:

- **[Evaluations](https://forecall.dev/en/docs/evaluations)**: real models choose and call your tools, and Forecall
  measures how often they get it right.
- **[Failures reported on your servers](https://forecall.dev/en/docs/dashboard#failures)**: what agents reported on
  your servers' tools, by error class, tool, model and client.
- **Larger allowances** for API keys and Failure KB lookups.

[Plans and billing](https://forecall.dev/en/docs/plans) compares the plans and their prices.

## What static scoring cannot tell

The score reads only the text of each description and schema, so keep these in mind:

- Short tools whose names already say what they do, such as `browser_close`, score low even when
  models use them well.
- A high score does not prove that models choose the tool well. It means the text gives them what
  they need. A low score points to the text worth improving.
- Scores are comparable only within the same version of the scoring rules. Every result shows the
  version it was scored with.

## Try it

Paste the JSON your server returns for `tools/list` at [the linter](https://forecall.dev/en/lint), or run the CLI
on a file. [Get your tools/list](https://forecall.dev/en/docs/tools-list) shows how to get the JSON.

```sh
npx forecall lint tools.json
```