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

Without annotations, the description discloses key behaviors: the paid nature ('call without x_payment to receive this call's exact terms...'), the liveness-scoring and eth_chainId probing of RPCs, and the EIP-3085 output format. It does not explicitly state 'read-only,' but the repeated 'returns' wording implies it. The payment workflow and data processing are transparently described.

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?

The description is information-dense but organized effectively: one sentence for the core record, one for the view modes, and one for payment/pricing alternative. Every sentence earns its place, though the middle sentence is long with multiple semicolon-separated clauses. No filler words; compact yet readable.

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?

With no output schema, the description adequately explains the return shape for each view (e.g., 'ranked, eth_chainId-probed RPC list', 'EIP-3085 wallet_addEthereumChain object'). It also details the payment response fields (amount, asset, network). It omits error handling or edge cases, but for a moderately complex read-only tool, the description is sufficiently complete.

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?

All five parameters are fully described in the schema (100% coverage), so the baseline is 3. The description adds value by semantically linking the view parameter to specific output shapes (e.g., 'view='wallet_config' returns a ready-to-submit EIP-3085 object') and by explaining the x_payment two-step flow beyond the schema's generic description. This exceeds the baseline.

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 opens with 'Canonical record for an EVM chain' which clearly identifies the resource and purpose. It then enumerates specific view modes (rpcs, wallet_config, search, l2s), distinguishing it from sibling tools like gas_price or spot_price. The verb 'returns' and detailed output shapes make the tool's function unambiguous.

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 provides explicit instructions for each view (e.g., 'view='rpcs' returns only the ranked, eth_chainId-probed RPC list') and explains the two-step payment flow. It also names an alternative: 'The free `pricing` tool lists every price at once.' This covers when to use, when not to use (for pricing), and an explicit alternative.

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