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

With annotations only marking this as non-read-only, open-world and non-destructive, the description adds substantial context: an auth requirement (owner key), a 60s rate limit, a suspended-agent precondition, the side effect of incident transitions, and an explicit negative scope statement about heartbeats.

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 short sentences, action front-loaded, no filler. The final two sentences are terse fragments, but each still carries a distinct fact (mechanism and negative scope) so little is wasted.

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?

An output schema exists, so return values need not be described. The description covers preconditions, limits, auth, and non-goals; the only real gap is that it never clarifies what the two required inputs should contain.

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 0% for both required parameters, so the description carries the full burden, and it does not. "owner key" loosely hints that api_key is a credential, but neither agent_id nor api_key is explained in a way an agent could act on beyond what the bare titles say.

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 gives a specific verb+resource ("Probe your registered endpoint now") and clarifies the mechanism as scheduled HTTP/TLS checks with incident transitions. It is distinguishable from siblings like agent_health_heartbeat, but it never names or contrasts with the adjacent agent_health_checks / agent_health_status 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 states a hard rate limit ("One per 60s"), a precondition ("paused agents must resume first"), and an explicit exclusion ("Does not send a worker heartbeat"), which routes the agent away from the heartbeat sibling. It stops short of naming a preferred alternative tool for any situation.

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