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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is the enumeration of what is returned — exit friction %, dollars received, measurement date, citation, and Kraken/Coinbase order-book comparison. This discloses behavioral traits beyond the annotations, though it omits freshness/refresh cadence for a time-sensitive measurement.

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?

Front-loaded with what is measured and why, then usage, then returns, then boundaries. Three dense sentences that each earn their place, though the enumeration of return fields makes it longer than strictly necessary.

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 no output schema, the description carries the return-value burden itself and does so: friction %, dollars received, date, citation, and the Kraken/Coinbase comparison. Nothing an agent needs to call or interpret this tool is missing.

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 the baseline is 3. The description adds meaning by spelling out the supported chains (Base, Ethereum, BNB Chain), which directly informs the optional 'chain' parameter even though the schema does not constrain it with an enum.

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?

States a specific verb+resource ('measures what a fixed-size sell of each tracked token actually returns versus its quoted price') plus the method (live DEX routing on Base, Ethereum, BNB Chain). An agent can distinguish it from exit_index and explain_transaction without opening a schema, and 'Not a price feed' blocks a likely misread.

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?

Explicitly enumerates the trigger questions: 'whether a token can really be sold, how liquid it is, or what they would get for a position,' plus a negative boundary ('not a price feed and not advice'). It never names the closest sibling, exit_index, so the agent must infer which measurement tool applies.

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