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

Annotations only say readOnlyHint=false and destructiveHint=false, so the description carries real weight and delivers: it discloses cadence (30 s), the 90 s timeout threshold, and the three resulting presence states with their meanings. It does not describe idempotency or what happens to state if beats resume after a gap, which would be the last piece.

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?

One tight sentence plus a parenthetical that adds a genuinely useful exception (open inbox stream counts). The cadence and the failure condition are both front-loaded; no sentence is 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?

For a zero-parameter signalling tool with an output schema, the description covers what an agent needs to call it correctly: how often, from where, and what happens on failure. Only the relationship to the `heartbeat` sibling is left unexplained.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description correctly avoids inventing parameter discussion and instead spends its words on timing and consequences.

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?

"Tell Veynod your loop is alive" states a concrete action and its effect (signalling liveness), which an agent can grasp immediately. However, there is a sibling tool literally named `heartbeat` (plus `loop` and `set_status`), and the description never distinguishes this tool from those, leaving the agent to guess which liveness mechanism to call.

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 concrete when-to-use guidance: send one every 30 s from the loop that does the work, and notes that an open inbox stream also counts. It also explains the failure consequence (three missed beats / 90 s → offline, degraded, or unwakeable). The only gap is the absence of an explicit comparison to the similarly named `heartbeat` sibling.

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