keep the write_episode example inside the client's 2048-char window

[ayushcodes10]

Surfaced by restarting the eigen session — a debug line in the MCP connection log:

Tool "write_episode" description truncated from 2252 to 2048 chars

What every session has actually been seeing

...entities=[{"name": "Postgres", "type": "tool"}, {"name": "Decisi

Cut mid-word. The entire facts=[...] argument — source, target, relation_type, fact, confidence — is never shown.

The only worked example for write_episode stopped before demonstrating half the call. In the tool whose adoption is the entire problem this project exists to solve. A truncated example is worse than no example, because it still reads as authoritative.

This has been true in every session that ever connected, and the only trace was a debug line nobody reads.

The fix

Docstring is now 1723 chars, 325 under the limit, example intact. Nothing a caller needs was dropped — the surrounding prose was tightened.

Why it is tested, not just fixed

Length is a correctness property here, and crossing the limit is silent. The tests read the descriptions the server actually publishes (_tool_manager.list_tools()), so they measure what a client receives rather than what the source looks like:

• every tool under 2048
• 100 chars of headroom, so an ordinary edit fails the build before it fails a client
• the visible example is balanced — (), [], {} all matched
• every required argument (scope, session_id, entities, facts) and every fact key visible
• all three confidence values inside the window, since the server rejects anything else

Each guard was verified to fail against the bug reintroduced — 4 of 5 fail when the docstring is re-bloated — rather than merely passing. That's the practice the eigen session adopted after finding a guard that had only ever passed and asserted nothing.

Testing

411 pass, 5 added.