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

Beyond the annotations (which already declare read-only, idempotent, non-destructive), the description discloses how results are delivered (webhook plus /v1/watch/alerts with a returned token), that no account is required, and the billing model (0.05 USDC via x402, 25 credits, first 5 paid calls free). Those operational details are exactly what an agent needs and are not in any structured field.

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 usage trigger is front-loaded in the first clause and the kinds and pricing follow in a dense but well-ordered sequence. It is somewhat run-on, mixing operational and billing facts into a single block, but nearly every sentence carries information an agent needs.

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 tool with no output schema, the description explains what the caller receives (a token used to read alerts at /v1/watch/alerts and the alert delivery path) and how to pay. All four parameters, the watch duration, and the alert channel are covered, leaving nothing essential unstated.

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 only 50%, so the description must compensate; it does, by explaining each enum value of kind (sanctions re-screened on EU/UN/UK/US list changes, company with COUNTRY:name, apk Dutch plate) and restating the value formats. The optional label parameter is not described, which is the one remaining gap.

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 specific action (watches one item for 30 days, recurring re-screening) with a clear resource, and enumerates the three watch kinds with their trigger conditions. This distinguishes it from the sibling one-shot screening tools (eu_sanctions_screen, pep_screen, company_lookup) without needing to open the schema.

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?

"Use for ongoing monitoring: the user wants to be told later or must show screening keeps running" gives a concrete selection trigger that separates it from one-off screening siblings. It stops short of naming an explicit alternative to use instead for a single check, so it is clear context rather than a full when/when-not routing rule.

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