fix: add schema constraints to MCP tool definitions

[Abiram08]

Reference Issues/PRs

Fixes #407

What does this implement/fix? Explain your changes.

Two small schema additions to server.py:

• Added enum to the task parameter in list_estimators — without
  this, LLM clients have no way to know what values are valid and tend
  to guess wrong
• Added minimum: 1 and maximum: 10 to cv_folds in
  evaluate_estimator — currently nothing stops a client from passing
  0 or a negative number

Both are missing constraints I noticed while reading through the tool
definitions. Small changes but they make the tools noticeably easier
to use correctly from an LLM client.

Does your contribution introduce a new dependency? If yes, which one?

No.

What should a reviewer concentrate their feedback on?

• Whether the enum values I picked for task are complete — I based
  them on the sktime docs but may have missed some
• Whether 1–10 is a sensible range for cv_folds or if the upper
  bound should be higher/removed

Any other comments?

Happy to extend this to other parameters if the approach looks good
to you — there are a few other places where bounds or enums would help.

PR checklist

For all contributions

• I've added myself to the list of contributors.
• I've added unit tests and made sure they pass locally.