Why
The README has exactly one worked example (end-to-end payment in tutorial mode). That undersells what the server can do — and the more curated example prompts a user sees, the faster they can spot the one closest to their use case.
A handful of natural-language prompts that drive multi-tool sequences end-to-end would double as:
- Documentation — concrete starting points for new users.
- Regression seed — feed them through the server periodically and check the LLM still completes them.
Scope
Acceptance
- A new user can pick an example closest to their goal, paste the prompt verbatim into their MCP client, and get a sensible result.
- The example list is referenced by #(LLM-friendliness audit issue) as the measurement corpus.
Why
The README has exactly one worked example (end-to-end payment in tutorial mode). That undersells what the server can do — and the more curated example prompts a user sees, the faster they can spot the one closest to their use case.
A handful of natural-language prompts that drive multi-tool sequences end-to-end would double as:
Scope
Acceptance