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

Goes well beyond the annotations by disclosing that malformed addresses return 400 uncharged, the $0.01/call price, the 25 free calls, and that failed calls are free — the last point is what makes the idempotentHint=false meaningful, since repeats are re-charged. It also confirms it reads/computes only and mutates nothing, consistent with readOnlyHint=true. Minor gap: no hint about latency or upstream failure modes.

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?

Front-loads purpose, then usage, then error handling, then example, then pricing/logistics — a sensible order with no filler sentences. It is dense to the point of feeling packed, but each clause (including pricing) conveys operationally relevant information.

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 compensates by enumerating the returned fields (contract vs wallet, bytecode size, EIP-1167 status, implementation). Combined with input format, error behavior, and cost, an agent has everything needed to call it and interpret the result.

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?

Only one parameter and schema coverage is 100%, so the schema carries the definition; the description adds a concrete example address and reinforces the 0x format, plus the malformed-input behavior. That is useful reinforcement rather than new semantics, so a 4 rather than a 5.

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 (check) and resource (whether a Sei 0x address is a contract or wallet) and enumerates the returned facts: bytecode size, EIP-1167 minimal-proxy status, and implementation address. The `sei_` prefix plus the chain-specific wording cleanly separates it from the many sibling `*_is_contract` tools.

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?

Explicitly says when to use it ('before sending funds or approving a spender') and names an alternative path for a broader need ('for a fuller risk verdict use check_counterparty'). That is a when-to-use plus an explicit alternative, not mere implication.

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