A minimal, production-ready scaffold for building accountable agents on Hedera.
This server has 7 tools with significant definition gaps. Most tools lack proper input schemas (only 2 of 7 have visible schema definitions). Descriptions are present but generic (avg ~80 chars, below the 194-char baseline). No output schemas documented. Tool names lack clear action verbs (e.g., 'fixatum_score' should be 'get_fixatum_score'). Parameters are minimally described. No error handling guidance. No tool annotations. This is a D-grade server with major structural issues.
Check Toolbox account balance and information.
Accept terms of service to enable paid tools on HederaToolbox.
Fetch the live Fixatum trust score for this agent. Free tool — costs nothing, no balance needed.
Scan an HCS topic for messages.
Write a record to the agent's HCS topic via HederaToolbox. Call this when something worth recording happens.
Screen a wallet for sanctions and identity checks.
Tool names lack action verbs. 'fixatum_score', 'hcs_write_record', 'account_info' do not follow verb_noun convention. Should be 'get_fixatum_score', 'write_hcs_record', 'get_account_info'.
Input schemas missing or incomplete for 5 of 7 tools. 'account_info' and 'confirm_terms' have empty input objects with no schema visible. 'fixatum_score' schema visible but minimal. No output schemas documented for any tool.
Descriptions are generic and under 100 chars for most tools. 'Check Toolbox account balance and information' (50 chars) lacks context on when to call or what it returns. Baseline is 194 chars.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
Query a Hedera token price.
No error handling guidance. Tools return success/failure but do not tell the LLM what to do on failure, whether to retry, or how to recover. No actionable error messages.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Risk levels are documented in the spec but not exposed to the MCP protocol, limiting agent safety reasoning.