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

With no annotations, the description carries the full transparency burden and does so well. It discloses the side effect (recording a successful run), the method (same as GETting the URL), the selfcheck payload variant, and the alerting behavior (trusted->challenged / recovery transitions only). This goes well beyond what the schema alone tells an agent.

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 dense sentences with no filler. The core purpose is front-loaded, then operational usage, then the selfcheck condition and alert semantics — every sentence earns its place.

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?

Covers purpose, invocation cadence, the selfcheck case, and alert semantics, which are the key things an agent needs to call it correctly. It slightly under-specifies what the call returns and does not explicitly route failure cases to record_failure, but for a simple ping/record tool this is adequate.

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 the schema already handles key and endpoints. The description adds a typical endpoint field shape and ties key to the URL path, but it does not materially extend the documented parameter semantics.

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 states a precise verb and resource: 'Record one successful run for a monitor' and anchors it to a concrete HTTP endpoint via the GET equivalent. This clearly distinguishes it from siblings like record_failure (failure vs success) and create_heartbeat/list_heartbeats (monitor management).

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 explicitly tells the agent when to call it: 'Call this every time your job runs.' It also gives a conditional rule for selfcheck monitors to pass an endpoints array instead. It does not explicitly name record_failure as the alternative for failed jobs, but the successful/failed contrast is strongly implied.

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