List NFTs

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

Annotations only state readOnlyHint=true and openWorldHint=true. The description adds meaningful behavioral context: GraphQL-backed with single query per kiosk page and no fullnode rate-limit risk, pagination semantics (next_cursor omitted when enumeration is complete), return contents (display metadata plus raw Move structs), and limit behavior. No contradiction with annotations; rich transparency is provided.

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 description is longer than average but every sentence carries operational value: scope, return shape, backend rationale, pagination details, limit, and alternative tool. Information is front-loaded with the core purpose before implementation details. Slight redundancy with schema (e.g., limit default) exists, but the overall structure is efficient and scannable.

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?

Given there is no output schema, the description adequately covers expected return fields (display metadata and raw Move contents) and pagination contract. It also names the network default and the alternative tool for count-only needs. For a read-only paginated list tool, nothing critical is missing for an agent to select and call it 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 coverage is 100%, so each parameter is already documented. The description adds practical semantics beyond the schema: cursor is 'from a prior response', next_cursor omission signals completion, and limit is capped at 1000 with default 50. This improves an agent's ability to form correct pagination loops, justifying a score above the baseline 3.

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-resource pair: 'List NFTs owned by a wallet', and expands scope with 'including kiosk-stored NFTs'. It clearly distinguishes this from sibling list_nft_collections (explicitly a count-only summary) and from list_owned_objects (which covers all objects, not just NFTs). A model can infer exactly what this tool does without opening the 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?

The description explicitly recommends this tool for NFTs, explains the pagination invocation pattern, and names the cheaper alternative list_nft_collections. However, it does not contrast with list_owned_objects or explain when to prefer that sibling instead. The guidance is strong but not exhaustive across all relevant siblings.

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