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

With annotations covering only the safety profile, the description carries substantial extra behavioral detail: a cron polls DexScreener every 10 minutes, the callback is HMAC-signed with a secret returned once, delivery is retried up to 3 times, alerts expire after 30 days, and polling returns one of THRESHOLD_MET/ok/FIRED/unknown. Pricing ($0.05 over x402, prepaid x-credit-token header, 1 free call/day) is fully disclosed. The readOnlyHint annotation sits somewhat oddly on a state-creating registration that persists for 30 days, but the description itself is candid about the state it creates.

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 action and trigger, and essentially every clause carries decision-relevant information (payment model, retry/expiry semantics, verdict values). It is nevertheless a dense single block that mixes invocation, billing, and return semantics; light structuring would improve scanability.

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?

For a paid, stateful tool with an output schema, the description covers what the agent needs: required inputs, webhook vs poll paths, auth/payment headers, delivery guarantees, lifetime, and the polling verdict vocabulary. Nothing material is left implicit.

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, but the description adds real semantics: up to/below for direction, USD for threshold, the https requirement for webhook, and that check is an alert id used only in polling mode. It doesn't clarify whether check can be combined with token/threshold/direction or must be passed alone.

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?

The description gives a specific verb and resource ('register a price-threshold alert on any Base token') plus the trigger mechanism (webhook when a token crosses your target). It is immediately distinguishable from read-only siblings such as token_price or multi_price because it is a persistent, paid registration with an expiry, not a one-shot quote.

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 clearly lays out the two operating modes and the condition that selects each: supply an https webhook URL to get pushed to, or 'omit the webhook and poll with check=<id>'. It also states the prerequisites (token, threshold, direction) and the payment options. It does not, however, route the agent away from the many sibling price tools (token_price, multi_price, rug_monitor) when a one-off or different kind of check is the better fit.

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