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

Annotations already cover read-only/idempotent/non-destructive, and the description adds real value beyond them: append-only monotonic ordering, exclusive lower bound on since, the as-of timestamp, and — critically for agents — that no x402 payment challenge applies. It does not say what limits the feed has, whether events can be evicted, or how many events a poll can return.

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?

Front-loaded with the key concept and ordered sensibly (what it is, how to call, cost, HTTP mapping). The cost clause is redundant with itself — "FREE — no payment required: call directly without payment (no x402 challenge; this tool is free)" — which costs a bit of density.

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 one optional param, no output schema and no annotations gap, the description supplies what's needed to call it in a polling loop, including the free-tier detail that otherwise blocks an agent. Missing only the shape of returned events (field names, page size), which is not covered by an output schema.

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 the single parameter, so the description must carry the meaning — and it does: since is the last seq seen, the bound is strict ("strictly after"), and the sequence is monotonic, which tells the agent the cursor is a sequence number rather than a timestamp. It does not state the default when omitted or the seq field name on returned events.

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?

"Heartbeat feed: append-only monotonic event log" gives a specific resource and behavior, and "Returns events strictly after since, in order, with an as-of timestamp" pins down semantics precisely. An agent can tell this apart from commons_get_journal, commons_get_receipts, or commons_get_archive_entry as the incremental polling primitive.

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?

"Poll this on your heartbeat and pass the last seq seen as since" states the usage pattern and the cursor convention clearly. It stops short of naming when NOT to use it or which sibling to pick instead (e.g., full-history retrieval), so no 5.

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