One hash per day: the Merkle digest of every reveal, hire deliverable and verification record stored on BNB Greenfield that day, with its root sealed on opBNB. Optional date YYYY-MM-DD, default the latest
| Name | Required | Description | Default |
|---|---|---|---|
| date | No |
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | ||
| days | No | ||
| root | No | ||
| found | Yes | ||
| leaves | No | ||
| sealed | No | ||
| verify | No | ||
| digestUrl | No | ||
| digestBytes | No | ||
| digestSha256 | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Because no annotations exist, the description carries the full burden. It explains the underlying aggregation and key settings, but the phrase 'sealed on opBNB' is ambiguous about whether the call is read-of state or performs / depends on an external sealing action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence front-loads the output concept with 'One hash per day', then states the data types, storage, sealing, and optional parameter config. No words are wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple—one optional parameter—and the output schema exists, so return details need not be duplicated. The description gives the core aggregation scope and endpoint config; the only minor missing pieces are edge-case behavior (e.g., empty dates) and a cleaner statement of side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has zero parameter descriptions, so the description fully compensates: it provides the exact format 'YYYY-MM-DD', says the date is optional, and specifies the default behavior as 'default the latest'. This is sufficient for the single parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a precise deliverable: the Merkle digest of every reveal, hire deliverable, and verification record on BNB Greenfield, sealed on opBNB. This distinguishes it from sibling list/verify tools, which operate at individual record level, not as a single merit root.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear usage context: the tool returns the daily Merkle digest, and the date can be omitted to default to the latest day. It does not explicitly name competing tools or conditions for choosing them, so it stops short of full then when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools occupy nearly the same territory: market_state, situation_report, and deep_report all present overlapping per-chain market analysis at different comprehensiveness levels. attest_spec and proof_spec are also near-identical, and attest_status, attestation_stats, and list_attestations use similar attestation vocabulary. Most data tools have unique jobs, but the overlapping report and verification tiers create real misselection risk.
The server consistently uses snake_case but mixes noun-style data endpoints like prices and wall_map with command-style actions like attest, buy_key, and verify_reveal. Report names are also uneven: market_state, situation_report, and deep_report signal only vague depth differences. The set is readable but does not follow a single predictable convention.
With 29 tools, this exceeds the heavy threshold and spans roughly four distinct functional areas: market data, attestation, key management, and webhooks. Each tool may earn its place individually, but the overall menu is too large for one MCP server; splitting it into data and attestation/administration servers would be clearer.
The attestation lifecycle is well covered with creation, status, listing, reveals, stats, and independent verification, and the key purchase and webhook workflows are also complete. The main gaps are historical-depth data, explicit key revocation, and a direct hire action despite hireable agents being listed, but agents can generally work around these. Core workflows do not dead-end.