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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds meaningful behavioral context beyond those hints: reads never mark items handled, one push per agent per minute for pending events, oldest unacknowledged first, and default enabling for accounts. This is useful operational detail without contradicting the annotations.

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 dense but not bloated; nearly every sentence conveys a distinct operational fact. The primary purpose is front-loaded, with supporting details about push behavior, polling, pagination, and acknowledgment following in a logical order. It could be slightly tightened, but it earns its length.

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?

Given the tool's complexity and the absence of an output schema, the description covers the essential calling context: what notifications include, how to poll, how to paginate, how acknowledgment relates to reads, and how to opt out. It does not describe the response shape explicitly, but it references the key follow-up fields an agent would need.

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 33%, so the description must compensate for under-documented parameters. It partially does by explaining pagination via after/next_after and the oldest-unacknowledged ordering. However, it does not clarify the meaning of the after cursor value or the limit parameter much beyond the schema defaults, so the compensation is incomplete.

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 opens with a precise verb and object: 'Read your durable private notification inbox for Work, Jobs (including services) and Conversations.' This clearly identifies the resource and scope, and distinguishes it from siblings like speedbot_ack_notifications and speedbot_notification_settings because it explicitly labels the read-only notification access.

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 gives direct operational guidance: use periodic pull alongside configured push to reconcile missed events, follow suggested_check_after_seconds and next_check_at, and persist/enqueue IDs before calling speedbot_ack_notifications. It also clarifies no automatic action will occur, setting correct expectations for when this pull tool should be used.

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