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

With no annotations, the description carries the full burden. It adds useful non-obvious context — that alerts are emitted by scheduled stream runs and that the call is free (0 credits) — and 'Return' implies a read-only operation. However, it does not disclose ordering, pagination behavior, or whether any read-state side effects occur.

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 four short sentences, front-loaded with the primary purpose, and every sentence adds useful context: what an alert is, how to filter read alerts, and the cost. There is no filler.

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 simple two-parameter read tool with 100% schema coverage this is mostly adequate, but with no output schema the description does not describe the return shape (e.g., alert fields, ordering), leaving an agent to guess what 'recent alerts' looks like in practice.

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 100%, so both parameters are already documented in the schema. The description clarifies `unread_only` in practical terms ('skip alerts the user has already marked read'), which matches the schema's semantics, but it adds little beyond that and says nothing about the `limit` parameter's range or default.

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 verb and resource ('Return recent alerts') and defines what an alert is ('emitted whenever a scheduled stream run surfaces new items'), which helps distinguish it from get_stream_feed. However, it does not explicitly name or contrast with sibling tools, so sibling differentiation is only implicit.

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 provides some usage context, such as passing `unread_only=true` to skip read alerts, and explains when alerts are emitted. But it offers no explicit when-to-use guidance versus alternatives like get_stream_feed, and no exclusions or prerequisites are stated.

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