opensea_collections

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

With no annotations provided, the description carries full burden. It discloses the max batch size (50), the single-upstream-request behavior, and the meaning of the `markets` array. It does not mention failure modes, auth requirements, or what happens with invalid exceeding slugs, but for a read-only lookup tool it provides substantially more behavioral context than a bare description would, so I only dock one for those omissions.

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 three sentences and front-loads the main purpose. Each sentence earns its place: purpose, differentiation from the single-collection tool, and clarification of the markets output. A mild redundancy exists between 'per-marketplace listed-item counts' and the later markets-array sentence, but it is not bloated.

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 the single simple parameter, complete schema coverage, and read-only nature, the description covers what an agent needs: what it fetches, the max batch size, how to format the slug list, and when to prefer it. While an output schema would further reduce uncertainty, the description self-reliantly describes the return contents well enough for an agent to invoke the tool 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 description coverage is 100%, so the schema already documents the `slugs` parameter as 'Comma-separated collection slugs, at most 50'. The description reinforces the comma-separated format and the 50 cap, but adds no meaningfully new parameter-level semantics beyond the batching benefit and return-field expectations, which are about behavior rather than parameter shape.

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 opens with a clear verb and resource ('Look up several OpenSea collections at once') and immediately differentiates itself from the singular `/opensea/collection/{slug}` tool by framing this as the batch variant. It also lists the concrete data returned (floor price, verification flag, headline stats, per-marketplace listed-item counts), so an agent can tell exactly what it is for.

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 instructs when to use it: 'Use this instead of calling `/opensea/collection/{slug}` in a loop' and gives the efficiency rationale ('it costs one upstream request regardless of how many slugs you pass'). This gives the agent an unambiguous rule for choosing between the batch and single-collection siblings.

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