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

Annotations already cover read-only/destructive/openWorld, and the description adds genuinely new behavioral facts: an 8 KB calldata cap, revert semantics (422 with reason, uncharged), pricing ($0.01/call, x402 or card key, first 25 free), and that repeated calls are billed — which explains why idempotentHint is false. This is exactly the extra context annotations cannot carry.

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?

Core semantics (read-only, latest block, no gas) are front-loaded in the first clause, and the example and limits follow logically. The pricing sentence is dense but earns its place by disclosing cost per call and free-tier behavior; a single pass covers everything.

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 still says the return value is raw ABI-encoded data requiring decoding, and it covers failure mode (422 + reason) and cost. Minor gap: it does not describe the response envelope or how errors other than reverts appear, but an agent has enough to invoke 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 100%, so the schema already documents to, data, and from. The description adds a concrete example pair (to=0xe15f..., data=0x18160ddd) and notes the result must be ABI-decoded, but says nothing about the optional from/msg.sender parameter beyond what the schema states. Baseline 3 is right.

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?

States a specific verb, resource, and chain: a read-only eth_call on Sei that sends ABI-encoded calldata to a contract at the latest block and returns raw data. It also positions itself against siblings by scoping to 'any view function that has no dedicated tool,' so an agent can tell it apart from sei_token_balance, sei_nonce, etc.

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?

Gives an explicit use case with a concrete worked example (USDC totalSupply, selector 0x18160ddd) and an implicit exclusion via 'has no dedicated tool.' It does not name which sibling tools take precedence, so the agent must infer the routing rule, but the context is clear.

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