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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false): discloses per-check cost drawn from prepaid credit, the required Bearer credit-token auth on the MCP transport, a top-up URL, the 50-active-watch-per-token cap, the HMAC-SHA256 signing scheme and header, and the webhook payload shape. This is unusually rich operational context.

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 core mechanic ('we poll for you') before cost, auth, and limits, and every sentence carries actionable information. It is dense and slightly run-on, packing signature, pricing, and rate limit into one long sentence, but nothing is wasted.

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 creating tool with no output schema, it covers the essential agent needs: cost, auth, limits, signing secret semantics, and webhook delivery format. The only real gap is what the create call returns (e.g., the watch_id and webhook_secret referenced but not described as return values).

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 only 40% schema coverage, the description compensates: it restates the interval_minutes range (5 to 1440), explains the webhook_url payload ({event, watch_id, service, result} per schema), and names the four valid service values. It still adds nothing about expires_in_days or the structure of the nested input object, so it is strong but not complete.

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 and resource ('we run page-watch, feed-watch, wallet-watch, token-watch every interval_minutes and POST to webhook_url') plus the exact trigger ('only when something changed'). This clearly separates it from sibling watch_list/watch_delete and from the one-shot siblings like page_watch, since it explains the polling delegation model.

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?

Implies the usage context well: use this when you want agentsvc.io to poll on your behalf rather than calling page-watch/feed-watch/etc. yourself repeatedly. It provides the interval bounds and the change-only delivery condition, but never explicitly states when NOT to use it or names the alternative tools to prefer for one-off checks.

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