Get metadata for specific CryptoPunks: type, traits with rarity percentages, and permalink. Rate limit: 10 per 10 min (read bucket — shared with browse_types, browse_traits, get_listings, get_floor_price, get_bids_for_punk, get_bids_for_merkle_root).
| Name | Required | Description | Default |
|---|---|---|---|
| punkIds | Yes | Punk IDs to look up (1-100) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true; the description reinforces this by calling it a 'read bucket' and adds a specific rate limit (10 per 10 min) shared with other tools. This adds useful behavioral context beyond the annotation, though it doesn't describe return format or error behavior.
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 exactly two sentences: the first explains purpose and outputs, the second provides the rate limit and shared bucket. It is front-loaded, efficient, and contains no unnecessary detail.
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?
For a single-parameter, read-only tool, the description covers purpose, outputs, rate limit, and read-only behavior. The schema covers the parameter, and while no output schema exists, the listed output fields (type, traits, permalink) are sufficient. Minor missing details like result ordering do not prevent effective use.
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?
The input schema fully describes the single parameter punkIds with min/max constraints and a description ('Punk IDs to look up (1-100)'). The tool description adds no further parameter semantics beyond the schema, so baseline 3 applies.
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 clearly states the tool's function with a specific verb ('Get') and resource ('metadata for specific CryptoPunks'), listing the exact outputs: type, traits with rarity percentages, and permalink. The use of 'specific' differentiates it from sibling browse tools like browse_types and browse_traits.
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 phrase 'specific CryptoPunks' implies the tool is for fetching details of particular punks, but there is no explicit guidance on when to use this tool versus alternatives, nor any mention of exclusions. The rate limit note lists siblings but does not direct selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool targets a distinct resource or action: trait/type browsing, punk metadata, listings/floor price, bids by root/punk, Merkle computation/filtering/resolution, and bid recommendations. The related Merkle tools have clear boundaries: compute builds a root from IDs, filter returns IDs for a trait selection, and resolve reverses a root only if it has bids.
All tool names follow a consistent `verb_noun` pattern in snake_case (e.g., browse_traits, get_floor_price, resolve_merkle_root). The two bid lookup tools use the same `get_bids_for_X` structure, reinforcing predictability.
Eleven tools is well within the ideal 3-15 range and each covers a necessary facet of the CryptoPunks domain—from market data (listings, floor) to trait-based bid analysis (merkle roots, recommendations). No redundancy or bloat.
The tool surface covers the full read-side lifecycle: viewing traits/types/punks, checking market prices/listings, analyzing existing bids, and supporting trait-based bid strategies through Merkle root operations and recommendations. It lacks write actions (e.g., placing bids), but the server's purpose is clearly analytical, so no obvious operational gap exists.