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

Annotations already declare this is a non-read-only, open-world, non-idempotent write, so the bar for added context is lower. The description still adds real behavior beyond them: a single-user immediate send returns its result inline while other targets answer asynchronously with status sending or scheduled, and a sk_test_ key limits delivery to test devices.

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?

Three sentences, each load-bearing: targeting rule first, response semantics second, key-mode caveat last. No filler and no restating of the tool title.

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 15-parameter, zero-required tool with no output schema, the description covers the two things an agent could get wrong: target exclusivity and what the call returns. Minor gaps remain around precedence when both template and title/body are supplied, but the schema descriptions carry that weight.

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 100%, so every parameter including all, topic, send_at, and idempotency_key is already documented in the schema. The description only restates the target exclusivity and the 1,000-item cap, adding no format or precedence detail (e.g., template vs. title/body) beyond structured data. Baseline 3 applies.

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 and resource (send a push notification) and enumerates the exact targeting modes: one user, a list up to 1,000, a topic, or everyone. That scope immediately distinguishes it from cancel_push, get_push, and list_pushes among the siblings.

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 a hard selection rule — 'Give exactly one target' — that tells the agent which of the four target parameters to set. It does not name sibling alternatives (e.g., use cancel_push to stop a scheduled send) or state when not to use it, which keeps it short of a 5.

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