AgentTrust

Tool annotations

32/35 tools have annotations

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

All four hints declared on every tool

3/35 tools missing one or more hints — submit_escrow_transaction (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_agent_wallet (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); fund_xrpl_wallet_via_coinbase (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). 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.

openWorldHint matches behaviour

4 tools claim openWorldHint=false but make outbound HTTP — get_wallet_verification_challenge → dynamic (line 977); rate_wallet → dynamic (line 1252); send_job_message → dynamic (line 1309)

Either flip openWorldHint to true (acknowledging external reach) or refactor the handler to avoid outbound HTTP. If the only network calls are to a known fixed endpoint that you consider part of the tool itself, document that and keep openWorldHint=false; otherwise true is honest.

Tests exist

No test files found

Add tests that exercise each declared tool.

Secrets stay with their owner

2 secret/sensitive values flow into network calls (GEMINI_API_KEY → dynamic, GEMINI_API_KEY → dynamic) (8 other flows matched canonical API hosts)

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

Secrets not logged

5 secret values sent to console.log

Redact or omit secret values from log output.