watchlist_deliveries

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

Annotations already establish the safe read profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower. The description nonetheless adds two non-obvious traits the annotations do not cover: the result is capped at the last 50 deliveries, and the call is free, which matters for a metered API with a sibling account_balance tool.

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?

One sentence carrying the scope, the 50-record cap, the outcome enumeration, and the cost note, with the scope front-loaded. No filler whatsoever.

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?

With no output schema, the description carries the return-value burden and does define the outcome vocabulary (delivered, retry, failed, no_credit) plus the row count. It omits what other fields each delivery carries and whether older deliveries are reachable, but for a simple read-only list tool this is close to sufficient.

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 a single required parameter and 100% schema description coverage, the schema already documents the id fully, so the baseline is 3. The description's phrase "one alert" is the only added semantics, and it slightly conflicts with the schema's "watchlist id" wording rather than enriching it.

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 result set (delivery records) scoped to one alert and enumerates the outcome vocabulary, so an agent can tell it apart from watchlist_get or watchlist_test. It never uses an explicit verb, and it calls the target an "alert" while the schema calls the parameter a watchlist id, a small terminology wobble that doesn't obscure the purpose.

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?

There is no when-to-use guidance and no reference to alternatives such as watchlist_get or watchlist_test, which an agent would plausibly confuse this with. Usage must be inferred from the resource name alone.

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