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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, but the description adds crucial context: the per-call payment via x402 from the caller's wallet, the fact that the first call returns paymentRequired and must be retried with paymentPayload, and that prices are indicative with the exact charge from the live payment challenge. This goes well beyond the annotations and illuminates the actual call flow.

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 lengthy but exceptionally well-structured with bulleted actions, pricing, required parameters, and defaults. Every sentence earns its place, and the front-loaded payment model gives immediate context. The structure is scannable and directly maps to the complex multi-action tool, making the length justified.

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 tool with 6 actions and 16 parameters, the description covers each action's purpose, pricing, required and optional parameters, defaults, and the non-trivial payment challenge flow. Since an output schema exists, there is no need to describe return values. Minor omissions like supported chains for token_prices are not essential for tool selection and invocation.

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?

Although the schema has 100% description coverage, the description enriches parameter understanding by grouping parameters per action, marking required parameters (e.g., 'Requires q', 'Requires ids', 'Requires tokens'), and clarifying critical semantics like using coin IDs rather than tickers. It also explains the paymentPayload lifecycle, which the schema only labels as a generic object.

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 identifies the tool as 'Crypto market-data lookups' with CoinGecko-sourced pricing and market data, establishing a specific verb+resource. It further enumerates six distinct actions (search, price_feed, market_data, historical_data, trending, token_prices), each with a clear functional role, making it easily distinguishable from sibling network/web3/travel tools.

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 provides excellent within-tool usage guidance, such as 'Call this first to resolve a coin id before using price_feed or historical_data' and explains market_data is for 'top N coins' / market overview questions. However, it does not explicitly contrast alternatives across sibling tools (e.g., when to use network.token_price instead), so it stops short of fully explicit when-not-to-use guidance.

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