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

Annotations already declare readOnly/openWorld/idempotent=false, but the description goes further by disclosing billing behavior (charged per call in USDC from the key's SingIt limits) and an account restriction (Base accounts only), which are not derivable from the structured fields.

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?

Two tight sentences: capability and returned fields come first, then usage and cost constraints. No sentence is filler, and the most decision-relevant alternative is front-loaded.

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 single-param read tool there is no output schema, yet the description compensates by listing the returned datasets, the alternative tool, the billing model, and the account restriction. An agent has everything needed to decide and invoke 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?

Only one parameter, and the schema already covers it at 100% with the example ticker formats (BTC, ETH, SOL). The description does not add format or validation detail beyond the schema, so the baseline 3 applies.

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?

It names the specific resource ('funding rates for one symbol across exchanges') and enumerates the bundled data (open interest, long/short ratio, large positions, liquidations), so the agent knows exactly what it gets back and how this differs from get_hyperliquid_market.

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 states the use case ('compare venues or gauge positioning') and gives an explicit alternative routing rule ('use get_hyperliquid_market for one Hyperliquid contract'), and adds the prerequisite that this is paid per call from SingIt limits in USDC, Base accounts only.

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