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

Goes well past the annotations by disclosing refresh cadence, the paywall/failure behavior in detail (PaymentRequired with no data), provenance of the shapes (backtest-confirmed on equities, forward-graded on crypto, disclosed per read), and what each hit carries (GO, fuel multiple vs BTC, grade and room). This is exactly the extra behavioral context annotations cannot convey.

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 first two sentences largely restate each other ('the coins showing a washed set-up shape, weighed against the same gate' echoes the opening question), and undefined jargon like 'gate', 'GO', and 'fuel multiple' costs readability. The paywall sentence is well placed at the end, and the core result shape is front-loaded.

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 must carry the return shape, and it does list the per-hit fields plus the full-universe setup column. It is slightly thin on result ordering and on what the two shape names mean concretely, but an agent has enough to call it and interpret the response.

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 zero parameters, so there is no parameter meaning to add; the baseline applies. The description correctly implies the call is unfiltered by stating it scans 'all of them' and returns 'the setup column for the full universe'.

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?

Opens with a direct question identifying the verb and resource ('which crypto coins show a set-up shape right now') and narrows scope to 'all 81 Robinhood-tradable coins' and 'the two WASHED SETUP shapes'. The phrase 'Live intraday version' signals the non-live sibling get_crypto_setups exists, but it never names it, so differentiation is implied 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?

It supplies useful context for choosing it ('live intraday', 'recomputed about every 5 minutes, 24/7') and states the access precondition (subscription or x402 wallet, otherwise PaymentRequired). What it lacks is explicit routing against the many siblings — get_crypto_setups, get_live_setup, get_crypto_trend_live — so the agent must infer when this scan is preferable.

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