send_push_notification

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

Annotations only declare the generic write/non-idempotent profile; the description adds concrete operational facts: PUSHNOTIF_API_KEY requirement, 1 credit per delivered device with a stated price, zero charge for 404/410 dead tokens that are auto-pruned, and that dispatch is irreversible. It also documents the segment fallback and the url default, which are behavioral, not just schema restatement.

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 action and its scope are front-loaded, and every sentence carries non-redundant information (alternatives, prerequisite, cost, irreversibility, segment/url behavior, return shape). It is a single dense block with several clauses chained into one long sentence, which costs a little scannability but wastes no words.

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?

Despite no output schema, the description enumerates the return fields (ok, campaign_id, total_targeted, total_delivered, total_gone_pruned, credits_deducted, credits_remaining). Combined with prerequisites, cost model, sibling routing, and irreversibility for a non-idempotent destructive-adjacent broadcast, an agent has everything needed to invoke it correctly.

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 100%, so the baseline is 3, but the description adds real semantics: segment as 'all' vs a custom tag sourced from update_subscriber_tags with tag-matching delivery behavior, and url defaulting to the app's registered site_url. It doesn't repeat title/body length limits, but those are already fully specified in the schema.

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 (broadcast), resource (immediate push notification), delivery channels (VAPID/FCM/APNs), and audience scope (active subscribers of a given app_id). It explicitly distinguishes itself from schedule_push_notification and configure_inapp_banner, so an agent can route correctly without opening a schema.

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?

Gives explicit when-to-use (instant real-time delivery), explicit when-not-to-use with the two named alternative tools, and a required prerequisite step (call list_apps first to obtain app_id). Nothing about tool selection is left to inference.

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