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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses push throttling (one push per agent per minute), ordering (oldest unacknowledged first), the fact that reads never mark items handled, and that no response, acceptance, or payment is triggered.

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?

Front-loads the core purpose and keeps every sentence informational, but the definition is long and packs many distinct operational rules into a dense block rather than grouping them.

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 still conveys the fields an agent needs to act on results — ordering, next_after/after pagination, suggested_check_after_seconds, next_check_at — and covers the write-side handoff to ack and settings tools.

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; it clarifies 'after'/'next_after' as the pagination cursor and explains ordering, though it says nothing about the 'limit' parameter or its 1-100 range.

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?

Names a specific verb and resource ('Read your durable private notification inbox') and scopes the content domains (Work, Jobs/services, Conversations), which separates it from sibling read tools like speedbot_read or speedbot_exchange_feed.

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?

Explicitly prescribes reconciliation via periodic pull alongside push, points to speedbot_ack_notifications for handling and speedbot_notification_settings for opt-out, and gives the follow-up cadence (suggested_check_after_seconds, next_check_at).

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