Create a watch (paid via x402)

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

With no annotations, the description carries the full burden, and it excels. It discloses the payment mechanism (gasless USDC signed locally), billing semantics (failed calls never billed), delivery pathways (HMAC-signed webhook and server-side mailbox), cryptographic receipts (Ed25519), and local storage of credentials. This is far beyond typical transparency and gives the agent a complete behavioral model.

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 description is a single dense paragraph, but every sentence earns its place, providing cost details, delivery routing, receipt handling, and billing guarantees. It is front-loaded with the purpose and immediately gives actionable pricing. While a bulleted structure would improve scannability, the prose is efficient and free of fluff.

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 creation tool with no output schema, the description covers the essential outcomes: it returns/remembers an id and secret, specifies event delivery, and explains billing failure behavior. It does not explicitly state the response shape, but the local storage phrase implies what the agent receives. Overall, it provides a complete mental model for invoking the tool.

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 description coverage is low (0% per context), so the description compensates for tier and webhookUrl: tier is explained with prices and limits, webhookUrl is noted as HMAC-signed. Conditions are partially described via examples like 'heartbeat dead-man switches' and condition counts, but the detailed condition shapes are left to the schema, which already contains them. This is adequate compensation overall.

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 opens with 'Buy a standing watch from DataSieve' – a specific verb and resource. It clearly distinguishes this creation tool from siblings by detailing the purchase aspect, tier pricing, and what constitutes a watch. The inclusion of concrete dollar amounts and trigger limits leaves no ambiguity about the tool's function.

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?

The description implies when to use this tool (to create a new watch) and even addresses the renewal scenario by explaining the 30-day tiers for agents 'that will not be awake to renew weekly.' It mentions complementary tools like drain_events but doesn't explicitly contrast with management siblings such as renew_watch or watch_status, so it stops short of full guidance.

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