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

Annotations already declare readOnlyHint=true, so the description doesn't need to restate safety. It adds behavioral context by explaining the sorting behavior ('diurutkan dari yang paling ekstrem') and warning that open_interest is a raw snapshot not notional USD, which is a crucial nuance. This goes beyond basic read-only disclosure and provides meaningful usage warnings.

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 sentences and front-loaded with the core function. Each phrase carries information: metric list, symbol count limit, sorting behavior, and sibling comparison. It is a bit dense but not wasteful; every sentence earns its place. Minor deduction for slight run-on structure, but overall efficient.

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?

While there is no output schema, the description covers the key aspects: what it compares, which metrics are available, sorting behavior, and the important OI notional warning. It also situates the tool among siblings. It doesn't detail return format, but for a comparison utility with these annotations and schema, the description is sufficiently complete for an agent to select and invoke 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 description coverage is 100%, so the baseline is 3. The description enhances this by explaining what each metric represents (e.g., funding_rate as 'funding terkini', top_trader_ratio as 'long% top trader terkini, by size posisi'). It also clarifies that symbols must be perpetual pairs and gives an example symbol list, adding practical meaning beyond the schema's basic descriptions.

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 'Bandingkan' (compare) and clearly identifies the resource: multiple Futures pairs. It states exactly what it does: compares 1 selected metric across 2-10 user-chosen symbols, sorted by extremity. It also distinguishes itself from sibling binance_scan_funding_extremes by clarifying that this tool is for user-selected pairs, not market-wide scanning.

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 explicitly contrasts with binance_scan_funding_extremes: 'Beda dari binance_scan_funding_extremes yang scan SEMUA pair di market -- ini untuk pair yang sudah kamu tentukan sendiri.' This provides a clear alternative and when to use this tool. It also enumerates the selectable metrics and includes a caution about open_interest being raw OI, not USD notional, which prevents misuse.

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