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

readOnlyHint=true is consistent with the description, so the safety profile is already covered; the description adds non-annotation context in the form of the max-10-NFTs-per-call batching limit and the nature of the returned payload (local ids vs decoded traits/fields). It does not say whether listing a large collection's ids is itself capped or paginated.

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?

A single front-loaded sentence that discloses both modes and the batch cap with no filler; every clause earns its place.

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 does the necessary work of characterizing both return shapes (list of local ids vs decoded traits/fields), which is enough to call it correctly. Minor gaps remain around pagination/listing limits and behavior for invalid or out-of-range ids.

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% and the schema's own 'ids' description already says 'Omit to list the collection ids' and carries the maxItems: 10 constraint, so the description largely restates structured data. It adds no format or addressing detail beyond the schema example ("#1#").

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 concrete verb and resource (explore an NFT collection) and spells out the two operating modes: list local ids when "ids" is omitted, decode on-ledger trait/field data when it is supplied. That is far more precise than the title 'Get NFT ids and data', but no sibling (e.g. get_resource_holders, list_claimable_stake_nfts) is named to anchor the boundary.

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?

"Without 'ids' it lists... with 'ids' it returns..." tells the agent exactly which input selects which behavior, which is real invocation guidance. It stops short of saying when to prefer this tool over sibling lookups such as get_component_state or list_claimable_stake_nfts.

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