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

With no annotations provided, the description carries the full burden and does well: it discloses that no ownerOf call is needed, that IPFS/Arweave/data URIs are resolved server-side (not just returned raw), the exact response components (tokenURI, metadata JSON, collection name/symbol), and the $0.002 cost. It omits failure behavior for nonexistent tokens or unretrievable IPFS content, and never explicitly says the operation is read-only, though 'metadata' strongly implies it.

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 core capability sentence is front-loaded and efficient, but the pricing and alternative routing is stated three times over ($0.002 appears in the 'Prefer /nft' clause, again standalone as '$0.002 USDC', and again in the 'Related:' tail with the same /nft and /chain/nft-owner comparisons). The 'Related:' block largely duplicates the preceding two sentences, so meaningful length could be cut without losing routing 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?

There is no output schema, so the description must describe return values and it does: tokenURI/uri, resolved metadata JSON, and collection name/symbol. Combined with the explicit cost and sibling routing, this is close to complete for a 3-param read tool; the remaining gap is that the structure of the resolved metadata object and the behavior on an unresolvable tokenURI are unstated.

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 0%, so the description must compensate. The worked example clarifies value formats — contract as a 0x address, token_id as a string like "1", chain as "ethereum" — which the bare schema does not convey. However, it never enumerates supported chain values or explains whether chain defaults to ethereum, leaving the highest-ambiguity parameter (chain, a free-form string with no enum) only weakly specified.

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 pair: fetches ERC721/1155 tokenURI/uri, resolves the JSON metadata from IPFS/Arweave/data URIs, and returns collection name/symbol. It explicitly distinguishes itself from owner-oriented siblings (chain_nft_owner) and the combined /nft endpoint, so an agent can tell it apart without opening any schema.

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 selection rules with prices: use this when only metadata is needed, use /nft ($0.002) when owner is also required, use /chain/nft-owner ($0.001) for owner alone, and /chain/erc721-tokens ($0.002) to list a wallet's token_ids. The 'Does not require ownerOf' and 'use when explorers ask for /chain/nft-metadata' lines pin the triggering context precisely.

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