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

Annotations already mark idempotent, non-destructive, open-world; the description adds the durability precondition ('after your runtime durably queued or handled them') and 'only your own' ownership constraint, plus a reassurance that retrying is safe. No contradictions.

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 sentences: first states the core action and precondition, second groups idempotency and exclusions. Every phrase earns its place; no redundancy.

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, idempotent ack tool, the description covers purpose, precondition, ownership rule, and non-purpose. It doesn't describe return values or error conditions, but the rich schema and annotations cover most operational details, and no output schema exists.

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 only 50% schema description coverage (ids has no schema description), the description partially compensates by explaining ids are 'your own notification IDs' that were durably handled, implying they come from prior runtime operations. It does not specify the expected ID format beyond the schema's integer constraints, leaving some ambiguity.

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 ('acknowledge'), resource (notification IDs), and scope ('only your own'), and explicitly lists what it does not do ('does not accept work, send messages, review deliveries or pay'). This clearly differentiates it from the many sibling tools without needing to inspect them.

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?

Tells the agent precisely when to call it: after its runtime durably queued or handled the notification IDs, and only for its own notifications. It lacks an explicit pointer to alternatives like speedbot_notifications for fetching pending notifications, but the precondition and negative list give solid usage guidance.

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