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

Annotations already declare readOnlyHint=true, but the description adds valuable behavioral context: it discloses the rate limit, the shared compute bucket, and the return format (punk IDs and Merkle root). This goes beyond the annotation and provides operational details without any contradiction.

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 concise and front-loaded: the first sentence states exactly what the tool does and its output, and the second adds the rate limit. Every word earns its place, with no redundancy or filler.

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 tool's moderate complexity, the lack of an output schema, and rich parameter schema, the description covers the essential context: what it filters, what it returns, and the rate limit constraint. It could mention pagination or result size limits, but the read-only annotation and clear return description make it sufficiently complete for an agent to use 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 description coverage is 100%, and the schema already provides detailed descriptions for every parameter, including the matchMode enum with explanations. The description only offers a high-level summary ('by type and traits') and does not add extra meaning beyond what the schema already conveys, so baseline 3 is appropriate.

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 ('Filter') with a clear resource ('CryptoPunks') and specifies the return value ('matching punk IDs and their Merkle root'). It clearly distinguishes this from sibling tools like browse_traits and compute_merkle_root by focusing on filtering while explicitly linking to related compute tools.

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 conveys usage context by stating the rate limit and shared compute bucket with compute_merkle_root and resolve_merkle_root, implying to use sparingly and coordinating with those tools. However, it does not explicitly state when to use this tool versus alternatives, so it stops short of a full 5.

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