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

Annotations only say read-only/non-destructive/open-world, while the description adds the genuinely important behaviors: the tool is metered per call, failure without payment returns isError with a fresh x402 PaymentRequired invoiceId, and the exact retry channel (_meta["x402/payment"] or payment_signature). It also states unpaid calls are free, which matters for an agent deciding whether to probe.

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-loads the price and the single question it answers, then the return shape, then the error/retry path – a sensible order. It is dense and repeats the price information already present in the title, which is mild redundancy but not padding.

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?

No output schema exists, and the description compensates by naming the returned fields and the failure object shape, plus payment requirements and retry mechanics. For a single-optional-parameter read tool, an agent has enough to call it and recover from the unpaid path; only a concrete example of the PaymentRequired payload is missing.

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?

With one optional parameter and 100% schema coverage the baseline is 3, but the description adds real sequencing meaning the schema does not: omit it on the first call, then supply the signed payload on retry, and it exists specifically for hosts that cannot set _meta. That is meaningful usage semantics beyond the schema text.

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 states a concrete scope: 'What is the worst current level across status pages, facilitator reachability, and recent changes?' plus the return fields (storm/level/reason, observed_* samples). This separates it from get_pulse_facilitator and get_pulse_providers, though it never names those siblings explicitly to say which one to prefer.

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 gives clear procedural guidance for the paid flow (omit payment on first call to receive requirements, retry with the signed payload; unpaid calls cost nothing) but no guidance on when to choose this aggregate storm signal over get_pulse_facilitator, get_pulse_providers, or get_service_status. Usage is implied by the 'one question' framing rather than stated as selection criteria.

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