NFT collection risk and quality analysis plus new-collection discovery (OpenSea + on-chain).
Scored across 2 tools
The two tools have clearly distinct purposes: one analyzes a specified NFT collection while the other discovers newly launched collections. An agent can easily choose between analyzing an existing collection and finding new ones.
Both tool names follow the same verb_noun snake_case convention: analyze_nft_collection and discover_new_nft_collections. The pattern is predictable and readable.
Two tools is thin for an NFT collection analysis server; useful workflows like looking up a specific collection or comparing collections are absent. However, the two tools are meaningfully scoped rather than redundant.
The surface covers discovery and risk analysis but lacks obvious supporting operations such as searching for a known collection, retrieving raw collection details, or comparing multiple collections. Agents can work around some gaps but may hit dead ends when asked to analyze a named collection.
Evidence-based NFT collection risk report: verified OpenSea market data, realized sales versus listings, creator evidence, risk flags, missing data and a confidence level. Not a profit prediction.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | free = overall score + short summary (limited per month); full = paid result via x402 (USDC on Base, sent in params._meta['x402/payment']); auto = full when a payment is attached | auto |
| chain | No | Chain of the contract (only used for contract addresses) | ethereum |
| identifier | Yes | OpenSea collection slug (e.g. 'boredapeyachtclub') or 0x-prefixed contract address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly and openWorld, so the bar is lower. The description still adds real context: the report is evidence-based on verified OpenSea data, separates realized sales from listings, and may include missing data plus a confidence level — telling the agent results can be partial or uncertain. It stops short of mentioning cost/rate-limit behavior in the prose, which is left to the schema.
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?
Two sentences, front-loaded with the core purpose and followed by a useful negative constraint. The single list-heavy sentence is dense but readable and wastes no words; a small structural refinement would earn a 5.
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?
There is no output schema, and the description compensates by enumerating what the report contains, including the confidence level and missing-data caveat. Parameters, payment tiers, and identifier formats are fully documented in the schema, so nothing essential for correct invocation is absent — only the paid-tier gating is unmentioned in prose.
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%, including detailed enum semantics for tier (free/full/auto with x402 payment mechanics) and chain. The description adds only the implication that the identifier resolves against OpenSea, so the baseline 3 applies; the schema does the heavy lifting.
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 specific verb and resource: it produces an evidence-based NFT collection risk report with named contents (market data, realized sales vs listings, creator evidence, risk flags, confidence level). An agent immediately knows what it gets back. It does not explicitly contrast with the sibling discover_new_nft_collections, so it falls just short of a 5.
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?
Usage is only implied: analyzing an already-known collection. The one scoping statement, 'Not a profit prediction,' bounds expectations, but there is no explicit when-to-use guidance, no mention of the discovery sibling, and no note that paid tiers exist for full detail (that lives only in the schema).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
New NFT collections launched on Ethereum and Base in the last day, week or month, found from onchain contract deployments and ranked by evidence-based risk analysis. Not a profit prediction. A full scan can take a few minutes.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | free = overall score + short summary (limited per month); full = paid result via x402 (USDC on Base, sent in params._meta['x402/payment']); auto = full when a payment is attached | auto |
| chain | No | all | |
| limit | No | ||
| period | Yes | Launch window: today = last 24 h, week = 7 days, month = 30 days |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real value beyond them by disclosing latency ('a full scan can take a few minutes') and framing the output as evidence-based risk ranking rather than a prediction. Paid-tier behavior (x402) is left entirely to the schema.
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?
Three short sentences, front-loaded with scope, then the methodology and the latency caveat. No filler; each sentence carries distinct information.
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 should hint at the shape of a result (a ranked list with scores and summaries), which it only gestures at via 'ranked by evidence-based risk analysis'. Paid-tier and limit semantics also remain unaddressed, so an agent cannot fully predict the response.
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 50%: tier and period carry descriptions, chain and limit do not. The description restores some meaning for chain ('Ethereum and Base') and period, but says nothing about how limit interacts with ranking (e.g., that it returns the top-N ranked results), leaving one parameter undocumented in both places.
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: new NFT collections launched on Ethereum/Base within a stated window, sourced from onchain contract deployments and risk-ranked. This is clearly distinct from analyze_nft_collection (discovery of new launches vs. analysis of one known collection), though the sibling is not named explicitly.
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?
Usage is implied by the 'new launches' framing, and 'Not a profit prediction' usefully sets expectations against misuse as a trading signal. However, it never states when to prefer this over analyze_nft_collection, nor any prerequisite or exclusion conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_nft_collectiondiscover_new_nft_collectionsNFT market data on 12 networks: floors, sales, trader profit, mints. Non-custodial trades.
Crypto intelligence: rug/scam scans for any token, verified whale flows, AI signals + track record
Rug pull risk and on-chain forensics for tokens on Solana and six EVM chains.
Pre-trade safety + wallets: Solana/EVM token risk, honeypots, counterparties, balances, txs, CVEs.
Add one secure layer between your agents and this server.
