Gexno Web3

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. The description adds useful behavioral context beyond annotations by naming the supported token standards, the returned metadata fields, and an example of expected output, though it does not mention failure modes or gateway/rate-limit 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?

The definition is front-loaded with the core action and return fields, and the example is useful. A few sentences repeat schema or annotation details, such as the tokenId format and read-only nature, but the description remains compact and easy to scan.

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 two-parameter tool with no output schema, the description is complete enough: it explains what is returned, which standards are supported, how tokenId may be formatted, and includes a concrete example. The annotations already cover safety and idempotency, so no critical information is missing.

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 both parameters are already fully documented in the schema. The description reinforces that tokenId must be a decimal string or integer and gives a concrete contract+tokenId example, but it adds little semantic meaning beyond the schema and its examples.

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 uses a specific verb and resource: resolve NFT metadata for a contract and tokenId. It lists the returned fields and the supported standards (ERC-721 tokenURI and ERC-1155 uri), making the tool clearly distinct from the only sibling, lookup_wallet.

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?

It gives explicit use cases: when the user asks for NFT metadata, token image, or IPFS NFT JSON parsing. It does not state when not to use it or name an alternative, but the sibling lookup_wallet does not overlap, so the missing exclusion is minor.

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

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the 'read-only lookup with no side effects' sentence is partly redundant. Where the description genuinely adds value is in disclosing the risk taxonomy and a non-obvious edge case: EIP-7702 delegated EOAs are reported as risk=eip7702 rather than as contracts, which an agent could not infer from annotations or schema.

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 the resource and outputs, then usage, then caveats, then example — good ordering with no filler sentences. Slightly longer than necessary because the read-only claim duplicates annotations and the example partly repeats the schema example.

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?

There is no output schema, and the description compensates by naming every returned field and showing a concrete return object. An agent knows what it will get back, what the risk enum values mean, and what the tool is not for — nothing material is missing for a one-parameter read tool.

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 the single address parameter is fully documented with a regex pattern and example, so the schema already does the work. The inline example call adds a little concreteness but no parameter semantics beyond what is structured.

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 and resource (look up an Ethereum wallet's on-chain profile) and enumerates exactly what is returned: ETH balance, contract status, outbound tx count, and risk heuristics. It is clearly distinguishable from the only sibling, lookup_nft, which deals with NFTs rather than address-level chain data.

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 explicit trigger conditions ('user asks to check a wallet, query address balance, or get a quick chain risk snapshot') and one clear exclusion ('Not an AML score'). It stops short of naming lookup_nft as the alternative for NFT queries, but the domain split is obvious enough.

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