Fetch a public HTTP(S) URL and return truncated text/json. Params: { url: string } (x402: 0.001 USDC per call)
HTTP equivalent: GET /x402/web-fetch Payment: x402 protocol — send X-PAYMENT header with base64 payment payload, or X-API-Key / X-Owner-Key / Bearer token to bypass.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only include a title, so the description carries the behavioral transparency burden. It discloses useful traits: the tool fetches public URLs, returns truncated text/json, and requires x402 payment (or auth bypass). It also indicates the HTTP equivalent and payment mechanism, which are beyond what annotations provide. However, it does not mention error handling, redirects, or rate limits.
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 appropriately concise and front-loaded. It opens with the primary purpose in one sentence, then adds parameter and payment details in separate lines. Every sentence contributes useful information without unnecessary verbosity.
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 URL fetch tool, the description covers the core behavior (public fetch, truncated output), the required parameter, and payment/auth details. There is no output schema, but the mention of return type partially compensates. The description is complete enough for an agent to distinguish this from other web-related tools, though it could include edge cases or error behavior.
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 is empty, but the description explicitly lists the parameter as { url: string }. This compensates for the schema gap, clarifying the expected input despite missing from the structured definition. While no additional syntax or constraints are given, the single URL parameter is straightforward.
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 states a specific verb and resource: 'Fetch a public HTTP(S) URL' and the return type 'truncated text/json'. This provides a clear purpose, but it does not explicitly distinguish it from sibling tools like web_search or web_markdown, though the focus on direct URL fetching is implied.
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 provides no guidance on when to use this tool versus alternatives. It does not mention scenarios where web_fetch is preferred over web_search, web_markdown, or http_check. The only usage-related information is the payment/auth mechanism, which is not about tool 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.
Multiple tool pairs are exact duplicates (e.g., wallet_analysis/wallet_analyzer, honeypot_check/rugpull_detector, defi_yield/defi_yield_rates) with identical descriptions, and many overlapping scanners (squeeze_scanner variants). An agent cannot reliably distinguish these tools.
Names are all snake_case, but conventions vary wildly: some are resource names (btc_price), some are actions (list_magnets), some are generic utilities (calculator), and duplicates use different naming patterns for the same function (wallet_analysis vs wallet_analyzer). No consistent verb_noun or resource_action pattern.
139 tools is an extreme count for any MCP server, far exceeding the 50+ threshold. The scope is a grab-bag of unrelated domains (crypto, FDA, SEC, utilities, web scraping), suggesting no curation.
The set is a shallow pile of read-only queries and utilities with no lifecycle management for any one domain. Many sub-areas have only one or two tools, and duplicates occupy slots where distinct operations should be. The lack of a clear domain makes completeness impossible to assess, but the surface is redundant rather than comprehensive.