crypto_news

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

No annotations are provided, so the description carries the full behavioral burden, and it does well: it discloses the cost ($0.0025 USDC per call), p99 latency (3000ms), the ranking/merging logic, and the exact fields returned per article. It stops short of saying whether results are paginated or what happens on an empty match, but the pricing and latency disclosure is genuinely useful context.

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?

Front-loaded with purpose, then output shape, then parameters, then cost/latency – a sensible ordering. It is dense but not padded, with the minor inefficiency of listing the source outlets twice (once in prose, once in the params line).

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?

With no output schema and no annotations, the description does the heavy lifting: it enumerates returned fields, filtering options, defaults, cost, and latency. Only minor gaps remain (pagination/empty-result behavior). Adequate for a 5-parameter, zero-required read tool.

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% (hours, limit, and sources carry no schema description), and the description compensates by naming all five parameters with example values (['BTC','ETH']), lookback range 1-168 default 48, limit 1-50 default 20, and the source list. It adds real meaning beyond the bare schema, though it largely restates the enum and bounds already present in structured fields.

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?

States a specific verb+resource ('Latest crypto news'), names the five upstream outlets, and explains the distinguishing feature: merged and ranked with duplicate stories grouped and boosted. An agent can tell this apart from news_search, news_sentiment, or rss_fetch without opening any schema.

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 says 'Filter by coins (tickers) or keywords,' which implies how to scope a call, but never states when to use this versus the many sibling news tools (news_search, rss_fetch, discussion_search, news_sentiment). Usage is inferable but there are no explicit alternatives or exclusions.

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