prime-silo

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

17/17 tools missing one or more hints — plan_workflow (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_workflow (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); stream_events (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +14 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — query_csv (line 126: result = eval(query, {"df": df, "pd": pd}))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool test coverage

11/17 tools referenced in tests (65%)

Write tests that reference each tool by name so every tool has at least one test.

No eval / new Function

3 eval() or new Function() calls — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Readable source code

1 file are minified or bundled, which is usually build output rather than concealment

Ship unminified, readable source.

Secrets never reach shell commands

2 secret values passed to shell commands — possible command injection

Never pass secrets through shell commands. Use library APIs that accept credentials as arguments.

Tool description accuracy

query_csv: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.