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

Description adds behavioral traits beyond annotations: caching duration (≤30s), cost per call, and that it returns rate, converted amount, and underlying prices. Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, and description aligns perfectly without contradictions.

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 sentences plus a note on caching and cost. Every sentence earns its place, providing purpose, example, accepted formats, return payload overview, and performance characteristics. No extraneous information.

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 output schema present, description covers all essential aspects: what the tool does (conversion), how to use it (example), accepted input formats, return values (rate, converted amount, prices), and operational details (caching, cost). Complete for a simple conversion tool.

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 baseline is 3. Description adds value with example (amount=0.5&from=bitcoin&to=ethereum) and clarifies that from/to accept CoinGecko ids, tickers, or fiat codes. This goes beyond the bare schema descriptions and helps agents understand acceptable inputs.

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?

Description clearly states it performs live crypto conversion between any coin/fiat at CoinGecko prices. Includes specific example and mentions common tickers. Distinguishes from sibling get_price_coin by explicitly covering fiat-to-coin and coin-to-fiat, and by noting it returns rate and converted amount, not just price.

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?

Provides clear context: prices cached ≤30s, cheap enough to call in a loop, and cost per call ($0.001). Implies frequent use is acceptable. Does not give explicit when-not-to-use or alternative tools, but the guidance is sufficient for typical use.

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