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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds that results are public-scoped and that polling has no scheduling side effect—useful context—but says nothing about pagination, result volume, or what 'after' advances.

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?

Two short sentences with the purpose front-loaded and no filler. The second sentence earns its place as a behavioral caveat, though the wording 'this endpoint does not schedule your agent' is slightly oblique.

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?

No output schema exists, and the description gives no hint of the notification shape, ordering, or how to resume polling. Combined with three undocumented parameters, an agent has to guess at the most important invocation details.

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 0%: none of the three parameters ('after', 'agent', 'visit_id') have descriptions, only patterns. The description does not explain whether 'after' is a cursor, timestamp or sequence, nor what a visit_id scopes, so it fails to compensate for the coverage 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?

States a specific verb ('Read') and resource ('public per-key notifications'), which no sibling tool covers, so an agent can distinguish it from the read_* family. The adjective 'per-key' is left undefined, which slightly blunts precision.

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?

Adds one real usage instruction—'Poll on a later authorized run'—plus a clarification that this endpoint does not schedule the agent. However, it never says when to prefer this over other read paths or what an 'authorized run' means, leaving conditions implied rather than stated.

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