Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnlyHint, openWorldHint, destructiveHint=false), and the description adds substantial non-obvious behavior: per-call cost ($0.0025 USDC), the x402 payment flow (USDC on Base/Solana/Polygon/Arbitrum, auto-paid by x402 MCP clients), a free sample call, and the exact fields returned per article. This is exactly the extra context annotations cannot carry.

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?

Purpose, ranking logic and output fields are front-loaded, and the pricing/sample details are pushed to the end where they belong. It is dense and every sentence carries information, though the param recap partially duplicates the schema constraints and the payment paragraph could be tighter.

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 fully compensates by listing the return fields (title, source, URL, publish time, 300-char summary, tickers, covering outlets) along with ranking behavior, filtering options, defaults and the payment requirement. An agent has everything needed to call it correctly and understand the cost.

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 only 40% (only coins and query are documented), but the description compensates by enumerating all five params with examples and ranges: coins e.g. ['BTC','ETH'], hours as a 1-168 lookback defaulting to 48, limit 1-50 defaulting to 20, and sources. Much of this restates schema min/max/defaults, so it adds meaning but is not fully additive.

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+resource (fetch latest crypto news) and adds real specificity: the named outlets (CoinDesk, Cointelegraph, Decrypt, The Block, Bitcoin Magazine) and the ranking methodology (grouped cross-outlet coverage ranks higher, newer ranks higher). It is clearly distinct from generic siblings like news_search in practice, but it never names or contrasts an alternative sibling 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?

It gives clear context for use: 'Filter by coins (tickers) or keywords', and supplies a concrete sample call {"coins":["BTC","ETH"],"limit":10} with a note that it is free. However it never states when to prefer this over news_search/news_sentiment or when the tool is not appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.