publish_notification

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

Beyond the annotations (idempotent, non-destructive, closed-world), the description discloses three things they cannot: the delivery precondition (a running controller), the delivery behavior tied to priority (important/urgent may be spoken when idle), and a prompt-injection safety contract that notification text must never be treated as instructions. It stops short of saying whether queued cards persist, expire, or return a handle for later dismiss/snooze.

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?

Four short sentences, front-loaded with the action, with the safety caveat and precondition placed after the core statement. Almost no waste, though the sentence fragments read slightly telegraphic.

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, so the description should at least hint at what comes back (an id usable with dismiss_notification/snooze_notifications) and it does not. The safety, idempotency and controller-precondition coverage is good for a mutation tool, but the five undocumented parameters and the missing return/expiry story leave real gaps.

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 0% across 8 parameters, so the description must carry the burden and it explains only two: dedupe_key (reuse to avoid duplicates) and priority (important/urgent may be spoken when idle). source, body, audio, group_key and group_title receive no meaning at all, leaving the grouping semantics and the audio enum entirely unexplained.

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+resource (queue a notification card) and adds that it is presented by the character, which separates it from display_message and from the read/manage siblings get_recent_notifications, dismiss_notification and snooze_notifications. It does not explicitly call out those siblings, so differentiation is inferential rather than stated.

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?

"Reuse a dedupe_key to avoid duplicates" and "Requires a running controller to deliver" are useful preconditions, but there is no explicit when-to-use-this-instead guidance against siblings like dismiss_notification, snooze_notifications or display_message. Usage is implied rather than routed.

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