Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (destructiveHint=false, openWorldHint=true) and the description adds real behavioral context beyond them: 'paged' reads with cursor/limit, a scan job that must be 'advance[d]', a 'priced' x402 query, and api_key auth for most actions. However, it never explains the notable tension that readOnlyHint=false while the tool is framed as a read surface (presumably the paid x402 path), nor does it mention cost, rate limits, or error behavior.

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 dense paragraph that is well front-loaded: purpose first, the sibling hand-off second, then the action catalogue. Each action gloss earns its place, but nine semicolon-separated clauses in a single block would scan far better as a list, and the actions/cost order is slightly buried.

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?

For a nine-action, 31-parameter mega-tool with no output schema, the description correctly covers the action surface and the field-to-action mapping. It stops short on the things an agent still needs: what each action returns, the payment/retry flow for the priced query when unpaid, and why the annotations mark it non-readOnly.

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?

Schema description coverage is 100% and every field already carries an '(actions: X)' tag, so the schema does the heavy lifting. The description's action glosses add some cross-field meaning (e.g. account = events or txs for one address, query = a priced x402 read on Base), but for the majority of the 31 parameters it largely restates what the schema tags already say.

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?

Opens with a specific verb and enumerated resources ('Reads blocks, transactions, logs, accounts and protocol state from the layer's own index and coord RPC') and then names each of the nine actions with a distinct gloss. It also actively differentiates from the sibling taifoon_prove ('For a proof use taifoon_prove'), so an agent can place it relative to the rest of the family.

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?

One explicit alternative is named with its selecting condition (proofs go to taifoon_prove), and the action glosses function as routing guidance (lookup vs logs vs account vs rpc vs query vs scan). What is missing is when-NOT guidance or disambiguation between closely related actions, e.g. rpc vs query, or logs vs account.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.