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

Despite annotations covering read-only and idempotent behavior, the description adds substantial context: it is a paid x402 endpoint costing $0.01, returns payment requirements and URL, and charges nothing on errors from unknown symbols, bad params, or stale data. It also discloses that the output is 'facts only, no recommendation' and lists the returned perp and news fields, giving agents a rich behavioral picture beyond structured hints.

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 dense but front-loads the paid nature and purpose before details. Every element, including error semantics, field list, and sample URL, earns its place for a complex paid tool; though long, it avoids filler and is well organized as a single informational paragraph.

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, the description carries the burden of explaining returns and does so thoroughly: it lists perp fields (mark, oracle, funding, OI, etc.), news sentiment fields, attention vs 7-day average, and neutral flags. It also covers payment flow and error behavior, making the definition complete for an agent to call it correctly.

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 coverage is 100%, so the single optional symbols parameter is already documented. The description still adds meaning by explaining the default behavior when omitted (watchlist plus coins in current news snapshots, up to 25) and by contrasting that with the 1-20 passed-symbol limit, supplementing the schema's min/max constraints.

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 and resource: 'one-call market scan' that returns Hyperliquid perp state joined with news sentiment. It explicitly distinguishes its scope from siblings by covering watchlist plus news coins (up to 25) or passed symbols (1-20), making it clear this is a combined perps+news context tool rather than a pure perps or sentiment endpoint.

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 clearly states when the tool is useful: 'for trading agents' and for scanning the watchlist plus every coin in current news snapshots, or user-supplied symbols. However, it does not explicitly name alternative sibling tools (e.g., get_perps or get_sentiment) or state when not to use it, leaving some routing to inference.

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