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

Annotations declare a non-read-only, non-destructive, non-idempotent write, which is a slightly ambiguous profile; the description resolves it by stating the check itself is untouched and no email is ever sent, clarifying that the only side effect is a queued inbox alert. It does not address repeat-call behavior (non-idempotent), which is the one trait annotations leave open.

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?

A single sentence with the action front-loaded and the caveats ('Never an email; the check is untouched') trailing compactly. No filler.

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, an agent could still want to know what the call returns or how to observe the test alert in the inbox, which is not stated. The safety profile and effect are otherwise fully covered for this simple two-required-parameter tool.

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% and each parameter already documents its source (instance_id from buy/list_utilities, heartbeat_id from heartbeat_add/status, passport_token header fallback). The description adds nothing about the parameters, so the 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?

The description names a concrete verb and resource ('Put one test alert ... in a heartbeat check's inbox') and pins the payload to the 'test' event, which cleanly separates it from a real heartbeat alert or the generic inbox_* tools.

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?

It gives a clear when-to-use rationale ('to check your handling before a job really stops'), which tells the agent this is a dry-run/preflight step. It does not name exclusions or point at heartbeat_add/heartbeat_status as alternatives, so it falls 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.