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

Annotations cover readOnly/openWorld/destructive, and the description adds substantial context beyond them: supported URI schemes (data:, https, ipfs:// via ipfs.io), truncation of strings over 1,000 chars including on-chain SVGs, metadataError surfacing for unreachable metadata, and per-call billing/25-free tier. 'Each call is charged, so repeats are not free' is consistent with idempotentHint=false rather than contradicting 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?

Front-loaded with the core behavior and the sibling routing, and the pricing/error details are genuinely useful. It is dense and leans on long comma-joined clauses, but almost every sentence carries information an agent needs.

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 tells the agent what comes back (tokenURI and parsed JSON fields), how truncation affects large values, and how failures are signaled (422 uncharged, metadataError). Nothing essential for correct invocation 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 coverage is 100%, so both parameters are already documented; the description adds an end-to-end example (contract=0x3d79..., tokenId=1) that demonstrates the expected contract format and clarifies that tokenId is a single whole number. Marginal but real value over the schema.

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 resource and verb: reads the tokenURI of one ERC-721 token id plus the JSON it resolves to, enumerating the fields (name, description, image, attributes). It explicitly separates itself from the sibling celo_nft_owner, so the agent can distinguish it without opening a 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?

'Use to show or check what an NFT is; for its owner use celo_nft_owner' gives an explicit use case and names the alternative tool for the adjacent need. It also covers the negative path (nonexistent token = 422, uncharged) so the agent knows what to expect when the call is wrong.

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