nft_metadataSingle NFT metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | ||
| tokenId | Yes | ||
| contract | Yes | ||
| refresh_cache | No |
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | NFT name | |
| image | No | Image metadata object | |
| media | No | Media objects | |
| tokenId | No | Token ID | |
| metadata | No | Additional metadata attributes | |
| description | No | NFT description | |
| contractAddress | No | NFT contract address | |
| timeLastUpdated | No | ISO timestamp of last update |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds no behavioral context beyond the annotations, such as caching behavior, chain handling, or response shape. It provides no extra value for an agent.
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 extremely short, but for a tool with 4 parameters and a specific purpose, this is under-specification rather than deliberate conciseness. It omits critical information that would fit in a few more sentences.
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 a 4-parameter schema, sibling tools, and an output schema, the one-line description is insufficient. It does not address chain defaults, the meaning of refresh_cache, or how this differs from nfts_for_collection. The output schema covers return values, but usage and selection context is missing.
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 schema has 0% description coverage, so the example is the only hint for parameters like contract and tokenId. The description does not explain any parameter semantics, nor does it clarify optional parameters like chain or refresh_cache. An agent cannot understand what inputs to provide beyond the example.
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 'Single NFT metadata' clearly identifies the tool's scope as metadata for one NFT, which distinguishes it from siblings like nfts_for_collection or nfts_owned. However, it lacks an explicit verb like 'retrieve' or 'get', so it's not a fully specified purpose statement.
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?
There is no guidance on when to use this tool versus alternatives such as nft_owners, nfts_for_collection, or nfts_owned. The description does not mention use cases or exclusions, leaving the agent to guess.
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.
Several tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta (currently described as identical), ask_pipeworx_grounded, and deep_research all serve question-answering/research, and the six Polymarket tools heavily overlap in finding and evaluating trading edges. Individual descriptions are detailed, but an agent could easily route to the wrong variant.
The set mixes conventions: Pipeworx tools mostly use verb_noun (ask_pipeworx, compare_entities, resolve_entity), but memory tools are bare verbs (remember, recall, forget), and the Ethereum tools are inconsistent (nft_metadata vs nfts_owned vs nft_owners, token_balances vs token_allowance). The lack of a uniform pattern makes the surface harder to predict.
At 40 tools, the server is oversized for the apparent core purpose of an Alchemy Ethereum interface. There is also significant redundancy: multiple ask/deep-research entry points and a dense suite of Polymarket analysis tools add bulk that could be consolidated.
The Ethereum side is mostly read-only convenience wrappers (NFTs, tokens, asset transfers) plus a generic eth_call catch-all, but lacks dedicated transaction sending, block/transaction detail, logs, or ENS conveniences. The rest of the tool surface is a sprawling collection of unrelated data-research, memory, and subscription features, making the overall implied domain incoherent and likely to leave obvious gaps for users expecting a focused Ethereum server.