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

Without the description the agent would not know about the 7-day polling window, one-shot alerting with hysteresis re-arming, or the $0.005 x402 payment flow and that an unpaid call returns 402 with requirements. These are exactly the operational facts annotations (readOnlyHint/idempotentHint) do not 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 purpose and payment sentences are front-loaded and efficient, but the trailing 'free alternative' sentence promotes an unrelated NVDA insider-trades sample and a trial endpoint, which does little to help invoke this specific crypto watch tool.

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?

Covers the trigger semantics, poll duration, and payment/error behavior needed to call it correctly with 6 params and no output schema. It stops short of describing what a successful watch returns (an id? a confirmation?) or how hysteresis thresholds behave numerically.

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 every parameter including the nested webhook object and idempotency_key is already documented in the schema; baseline 3 applies. The description adds only the conceptual 'hysteresis' notion, which maps to no named parameter.

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 concrete verb+resource ('Monitor a crypto price') with scope detail: runs between agent turns, alerts once on threshold cross, re-arms via hysteresis. This distinguishes it from the check_* siblings by its async/alerting nature, though it never explicitly names check_crypto_price or the generic create_watch as the alternatives.

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?

'Monitor a crypto price between agent runs and alert once when it crosses a threshold' gives a clear usage context (background monitoring vs one-shot checks) and the payment/free-trial notes tell the agent how to get a free look. No explicit when-not guidance or named alternative among sibling tools.

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