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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that: it discloses the return content (count plus top-3 hits by grade with GO, fuel vs BTC and room), labels the data as backtest-confirmed on equities and forward-graded on crypto, and explicitly frames it as 'a descriptive marker, not advice.'

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?

Three tight sentences, front-loaded with the scan scope before the return payload and the caveats. Nothing redundant, and the 'not advice'/'Free' trailers are short and purposeful.

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 and no input parameters, the description carries the burden of describing the response and does so ('how many... plus the top-3 hits by grade with GO, fuel vs BTC and room'). It stops short of explaining what GO/fuel/room measure or data freshness, which leaves minor gaps for an agent interpreting the payload.

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 tool takes no parameters and the schema is empty, so there is nothing for the description to document. A 4 baseline is appropriate.

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 and resource ('Crypto SETUP scan PREVIEW') and quantifies the scope (81 Robinhood-tradable coins, two washed-shape SETUP patterns). 'A live trimmed slice of the full scan' implicitly separates it from the fuller scan siblings, though it never names get_crypto_setups_live, so differentiation is inferential rather than explicit.

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 word 'PREVIEW' and 'trimmed slice of the full scan' imply when this is the lighter-weight option, but there is no explicit when-to-use, when-not, or named alternative. An agent must infer the routing from the sibling names.

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