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

Annotations only give the generic write/open-world/non-idempotent profile, and the description goes well beyond them: the scheduler cadence and default, re-arming after the condition clears, completion after max_fires, the signed POST fire report, and the important clarification that "Version 1 sends reports and moves no money." It also discloses the x402 payment path, the shared free-call allowance, and the X-Wever-Wallet-Proof requirement, which is exactly the kind of auth/pricing context an agent needs before calling a paid endpoint.

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 paragraph is front-loaded with the core contract (target, condition, callback, expiry) before payment and routing details, so a skimming agent still gets the essentials first. It is dense and partly overloaded with commercial mechanics, the /api/watch-contract pointer and the human page URL, but almost every clause carries operational meaning.

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, open-world, asynchronous tool with no output schema, this is close to complete: it names the return artifact (a report with an Ed25519 signed receipt), the auth headers, the cost and free tier, and the watch's full lifecycle. Nothing material an agent must know before invoking it appears to be 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?

Schema description coverage is only 57%, so the description has to carry weight, and it largely does: it explains the three target variants, the condition field/operator/threshold structure, the default check_interval_seconds of 300, and max_fires defaulting to 1. It also adds a real constraint the schema lacks (expires_at "up to 30 days ahead") and states the no-money-movement semantics of a fire, though the optional label parameter is never mentioned.

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 a specific verb and resource: "register a standing instruction for the paying wallet," then enumerates the three target families and the condition shape. An agent can immediately distinguish this from wever_watch-list, wever_watch-status and wever_watch-cancel, which are separate lifecycle operations on an already-created watch.

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 makes the use case clear (a recurring server-side check that fires a callback instead of requiring repeated polling), and the line "One call covers every check until the watch ends" tells the agent this replaces a polling loop. It does not explicitly name sibling alternatives or state hard exclusions, so it stops short of a 5.

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