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

Annotations only flag it as a non-destructive write with open-world effects; the description adds a lot beyond that: the key is returned only once, the cursor/key must be saved, the initial snapshot is self-reported and not verified reachability, 10 creation attempts/IP/day, and no push delivery. These are non-obvious traits an agent must know before calling.

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?

Dense but every clause carries load-bearing information: key rules, return-value persistence, snapshot caveat, rate limit, delivery mode. Front-loaded with the action and target constraints, and there is 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?

Despite an output schema, it usefully warns that subscription_key and cursor are returned only once and must be saved, plus rate limits and the self-reported nature of the snapshot. Nothing an agent needs to invoke or correctly consume the subscription is missing.

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%, so the description must carry both parameters. It explains api_key semantics (omit for public targets, owner key for private) and constrains agent_ids to 1–20 existing heartbeat agents, which is meaningful beyond the bare schema types.

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+resource+scope: 'Opt in to a seven-day pull feed for 1–20 existing heartbeat agents.' It is clearly differentiated from siblings like delete_liveness_subscription and read_liveness_events, which handle removal and consumption of the same feed.

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?

Explains the key requirement: public targets need no key, private targets require the owner's api_key, which tells the agent when and how to invoke it. It does not explicitly name read_liveness_events/delete_liveness_subscription as the downstream alternatives, so routing guidance is implicit via 'pull feed' and 'No push delivery'.

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