Full risk assessment for a token. Returns risk score (0-100), risk level, confidence, recommendation (PROCEED/REQUIRE_HUMAN_APPROVAL/BLOCK), reasoning, and flags triggered. Equivalent to GET /v1/risk/{chain}/{address}.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | Yes | Blockchain to query: "solana", "base", "ethereum", "arbitrum", "bsc", or "hyperevm" | |
| address | Yes | Token mint address (Solana) or contract address (Base/EVM, 0x-prefixed) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, placing the full burden on the description. The description only lists return fields and API equivalence, without disclosing whether the operation is read-only, any side effects, authentication needs, or rate limits. The implication of a read operation is weak.
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?
One sentence plus the API equivalent, no redundancy, every sentence adds value. Concise and well-structured.
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 simple two-parameter tool with no output schema, the description lists key return fields (score, level, confidence, recommendation, reasoning, flags), which is fairly complete. However, it does not explain the meaning of recommendation values or risk levels, leaving some gaps for an AI agent.
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 100%, so the description adds no extra parameter semantics beyond what the schema already provides (chain and address). The API endpoint hint reiterates the parameters but does not enhance understanding.
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 performs a full risk assessment and specifies the return fields (risk score, level, confidence, recommendation, reasoning, flags). It distinguishes from siblings by using 'full' implying comprehensiveness, but does not explicitly differentiate from 'quick_check' or 'contextual_risk'.
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 implies 'full risk assessment' as the use case, with a guideline being the equivalent API endpoint. However, it lacks explicit direction on when to prefer this tool over siblings or any caveats like required permissions or data freshness.
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.
The two tools are mostly distinct: analyze_token provides a basic risk assessment, while contextual_risk adds position-aware context. Since contextual_risk is a superset, there is slight overlap, but the descriptions clearly differentiate the use cases.
Tool names do not follow a consistent pattern. 'analyze_token' uses a verb_noun structure, while 'contextual_risk' uses an adjective_noun structure. This inconsistency could confuse agents expecting a uniform naming convention.
With only 2 tools, the server feels minimal, but for a narrowly scoped risk-assessment domain, this count is borderline acceptable. It is slightly below the typical 3-15 range but not unreasonably sparse.
The tool surface covers the core risk assessment functionality with both basic and contextual variants. Minor gaps exist (e.g., batch analysis or specialized chain-specific queries), but the primary workflows are supported without dead ends.