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

The description goes far beyond annotations: it explicitly states 'READ-ONLY. Does not place orders, move funds, or mutate your exchange account.' It adds caching behavior ('Responses may be cached (~2700s)'), auth requirements (X-Api-Key/x402), cost ($0.003 USDC), rate limit (30/min), and a note that linked Connect keys are free. This is exceptionally thorough and consistent with the readOnlyHint and idempotentHint annotations.

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 well-structured with labeled sections (Behavior, Auth, Cost, etc.), but it contains redundancy: the opening sentence repeats the 'Purpose:' phrase verbatim. It is longer than necessary for the value added, though the labeled structure helps scannability. The repetition of the exact same sentence is wasteful, so a medium score is appropriate.

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?

Given the tool's complexity (auth, cost, rate limits, caching, output type), the description covers every relevant aspect: what data is returned, how it behaves, how to authenticate, what it costs, rate limits, and usage guidance. Since an output schema exists, it does not need to detail return values, but it explains the output as 'normalized market microstructure data.' This is a complete context package for an agent.

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?

The schema already documents both parameters with full coverage (100%), including the symbol default and the __x_payment retry use case. The description does not add additional parameter-level semantics beyond what the schema provides; it merely references the __x_payment in the auth section. Thus the baseline 3 applies as the description is not needed to compensate for missing schema info.

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 clearly states the tool provides 'Comprehensive Coinglass derivatives data including open interest, liquidations, funding rates, and long/short ratios' – a specific resource with explicit data types. This distinguishes it from narrower siblings like cc.funding_rates and cc.open_interest. The title 'Aggregated Derivatives Intelligence' reinforces its role as a comprehensive aggregate.

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 Guidelines section says 'Use for research / signal context' and recommends pairing with cc.agent_strategy before any live order, providing clear context. It also warns 'Do not invent fills from this data alone,' but it does not explicitly contrast with alternative sibling tools or state when to choose a more specialized tool. This is clear usage guidance but lacks explicit exclusions.

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