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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real value on top: the outcome vocabulary (valid/weak/invalid), the 0-100 score, per-setup failed checks, and a full price ladder (0.50 base, 0.35 above 10 payments, 10-pack). It does not discuss failure modes such as network/price-feed outages or what happens to setups beyond the 10-item cap, so it stops short of exhaustive.

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 the core capability, then cost, then the recommended next step — a logical order with very little waste. The parenthetical price ladder and the 'next field' note are dense but each carries decision-relevant information; the single run-on block is harder to scan than short labeled segments would be.

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 correctly compensates by describing the return payload: per-setup verdict, 0-100 score, failed checks, and a 'next' field pointing to the follow-up call. Combined with schema-documented payment parameters, an agent has enough to invoke and interpret results; only edge behavior (partial failures, payment errors) is left to the schema's error hints.

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?

At 75% schema coverage the schema documents symbol format and the payment/bundle/payer options, so the baseline is already 3; the description adds the 10-setup ceiling framing (reinforcing maxItems) and the pricing-tier context that gives meaning to payment_tx, bundle_token and payer_address. It adds no field-level semantics for tp1/tp2 or entry/stop relationships, which keeps it at 4.

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 (pre-trade validation of crypto setups) plus the batching scope ('up to 10 ... in one call') and enumerates the checks performed (geometry, stop vs 1h ATR, R:R, 1h/4h trend, RSI14, entry distance). An agent can immediately tell this apart from the single-setup sibling validate_setup by the batch scope and multi-setup return shape.

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?

Gives explicit downstream sequencing: after validating, run historical-gate on the best valid setup, and notes the result's 'next' field carries the exact call. It also surfaces pricing tiers so the agent can weigh cost. It never states when NOT to use batch (e.g. a single setup) or names validate_setup as the alternative, which keeps it below a 5.

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