token_verdictHeuristic ERC-20 safety verdict on Base: bytecode risk capabilities, ownership, metadata, 0-100 score, hold/caution/avoid. $0.01 per call.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ERC-20 token contract address on Base (0x-prefixed, 42 chars) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool read-only, open-world, and idempotent. The description goes beyond this by revealing the heuristic nature of the verdict, the factors examined, and the $0.01 per call cost, which is useful behavioral context that the annotations do not provide.
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 a single, information-dense sentence that front-loads the main outcome and then adds methodology, output scale, and cost. Every clause earns its place, with no redundant 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?
For a single-parameter tool with strong safety annotations, the description covers what the tool checks, the verdict scale, and the pricing implication. Without an output schema, it briefly summarizes the return values enough for an agent to call it, though it stops short of giving exact output shape or sibling differentiation.
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 single parameter, address, is fully documented in the schema with format and chain constraints, so schema coverage is 100%. The description restates 'on Base' but adds no new parameter semantics or constraints beyond what the schema already provides, so the baseline score of 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 names a specific deliverable — 'Heuristic ERC-20 safety verdict' — and the target chain, Base. It also lists concrete outputs such as bytecode risk capabilities, ownership, metadata, a 0-100 score, and hold/caution/avoid categories, which clearly distinguishes it from siblings like verify_token or data_token_activity.
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 purpose implies when to use it: when an ERC-20 token safety assessment on Base is needed. However, it does not explicitly say when to prefer this over siblings such as verify_token, nor does it provide exclusion criteria or when-not-to-use guidance.
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.
Most tools are cleanly separated by domain prefix (data_, security_, validate_, verify_) and describe distinct outputs. A couple of pairs like token_verdict vs verify_token or data_portfolio vs wallet_dossier could be confused until descriptions are read, but the descriptions resolve the ambiguity.
The majority of tools follow a predictable prefix_subject pattern, e.g. data_block, security_tls, validate_iban, verify_payment. A few outliers like html_to_markdown, text_diff, wallet_dossier, and token_verdict use different conventions, but the overall system remains readable.
20 tools is on the heavy side for the typical MCP server and sits in the 16–25 'feels heavy' zone. Most tools have a legitimate purpose, but the five validate_* identifier tools plus two generic utilities could feel like surface area bloat.
The server covers a broad and coherent read/validation domain: chain data, token safety, payments, security checks, and identifier validators. Minor gaps exist, such as lack of detailed historical transaction/activity data and no general network/domain security scan beyond email, TLS, and typosquat.