http_fetchFetch a web page and extract its main text content. Useful for reading articles, documentation, and web resources. Returns cleaned text, not raw HTML.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to fetch (http or https only) | |
| max_chars | No | Maximum characters of extracted content to return |
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| title | Yes | ||
| content | Yes | ||
| truncated | Yes | ||
| content_length | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already signals a safe read operation. The description adds useful behavioral context by stating that it 'extracts main text content' and 'returns cleaned text, not raw HTML,' which sets expectations for the output. It does not disclose potential failures like JS-dependent pages or redirects, but the annotation lowers the burden.
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 two short sentences that are front-loaded with the core purpose, then provide a use case and output format. Every sentence adds value and there is no redundancy or padding.
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 an output schema, a read-only annotation, and a clear description of behavior and output format, the description is complete. The cleaned-text return behavior is explicitly stated, and schema details cover the rest.
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 descriptions cover 100% of the parameters, providing details on URL format and max_chars bounds/defaults. The description itself adds no extra parameter semantics beyond the schema's coverage, so baseline 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 uses a specific verb ('Fetch') and resource ('a web page') and clearly states the operation ('extract its main text content'). It also differentiates from sibling tools like web_search by focusing on fetching a given URL rather than searching, and notes the output is cleaned text, not raw HTML.
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 gives clear use cases: 'reading articles, documentation, and web resources.' However, it does not explicitly mention alternatives or when not to use this tool (e.g., 'use web_search when searching for pages'), so it stops short of full exclusion 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 target distinct blockchain/DeFi resources and actions. A few pairs like get_lending_rates vs get_yield_rates and get_defi_positions vs get_liquidation_risk have overlapping boundaries, but detailed descriptions and explicit redundancy notes (e.g., get_eth_balance vs get_wallet_portfolio) reduce confusion.
All tools follow a consistent snake_case verb_noun pattern (e.g., get_block, convert_currency, decode_transaction). The only minor deviations are noun-first names like http_fetch and web_search, but the style is uniform and predictable.
At 27 tools, the server exceeds the 25-tool threshold for 'too many' and feels heavy. While the breadth of DeFi and crypto features justifies some size, the number is unwieldy for an agent to scan efficiently and could be consolidated (e.g., merging balance-related tools).
The tool surface covers a wide range of blockchain data: balances, prices, TVL, yields, DEX quotes, gas, block/transaction details, approvals, and DeFi positions. Gaps include lack of wallet transaction history and NFT support, but these are beyond the server's clear focus on read-only DeFi analytics.