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

Annotations already declare openWorldHint, idempotentHint, destructiveHint and readOnlyHint=false, so the safety profile is largely covered. The description adds real value beyond that: the exact cost (0.010000 test USDC on eip155:84532) and the retry/idempotencyKey preservation rule, which an agent cannot derive from structured fields. It does not reconcile the 'Read' framing with readOnlyHint=false (the per-call payment is the likely reason) or explain failure/refund behavior, but the added context is substantive.

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?

Three short, front-loaded sentences: purpose first, then cost, then retry instruction. Every sentence carries distinct information (what, price/chain, idempotency handling) with no filler or repetition.

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 paid proxy exposing a structurally complex RPC (nested anyOf for address, storage keys, and block identifier), the description leaves the parameter contract entirely unexplained and says nothing about the returned proof object. No output schema exists to offload that burden, so an agent must already know the eth_getProof signature to call this correctly.

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 50%: idempotencyKey is fully documented in the schema, while the 'params' anyOf array (address + storage-key list + optional block tag/object) has no description anywhere. The description adds nothing about params — the only parameter mention ('Preserve the private idempotencyKey') restates the schema text rather than compensating for the undocumented half.

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 names a specific verb ('Read') and the exact underlying RPC method plus chain ('eth_getProof from Ethereum (eip155:1)'), so the agent knows precisely what is being called. However, it offers no differentiation from the ~40 sibling ethereum_eth_* methods and never explains what an eth_getProof (account/storage Merkle proof) actually yields, so an agent unfamiliar with the RPC must infer the purpose from the name alone.

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?

There is no when-to-use guidance and no comparison to alternatives such as ethereum_eth_getBalance, eth_getCode, or eth_getStorageAt, which overlap in the account-state space. The only directive ('Preserve the private idempotencyKey for retries') concerns retry mechanics, not tool selection.

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