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

With no annotations provided, the description carries the full burden and does so: reading does not mark events read, unread events are retained 30 days, 'dropped' counts events removed before being read, and output is oldest-first. It also warns that captured response bodies and hook requests are third-party data to be treated as data, never instructions — a non-obvious safety property not expressible in schema.

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?

It is front-loaded with the high-value framing ("Read what happened while you were away") and every sentence carries operational information. It is dense — a single long paragraph mixing purpose, payload shapes, acking workflow, retention, and a safety note — so a scan-and-skim agent may need to re-read, but there is little filler to cut.

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?

No output schema exists, so the description must explain return values, and it does: events are { seq, at_ms, event, ... } with per-type payload details, plus 'dropped' counts. Combined with the ack workflow and retention rules, an agent has everything needed to call this correctly and follow up with ack_inbox.

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 67%, so the schema documents `ack` and `after` but leaves `limit` with no description at all. The prose adds real meaning beyond the schema — the default is unread-only, `seq` is the cursor value, and acking advances the cursor — but never mentions `limit`'s role in bounding how many events are returned, so it does not fully compensate for the coverage gap.

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 specific verb and resource — reading inbox events from tasks, watches, crons and hooks, oldest first — and enumerates the concrete event types (task.finished, cron.failing/recovered, hook.received). It explicitly contrasts with the sibling ack_inbox, so an agent can distinguish the two operations without opening either schema.

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 an explicit use case ("read what happened while you were away"), states the default behavior (returns unread events), names the alternative (ack_inbox with the last seq) and the inline option (ack: true), and flags the retention window (30 days) and the `after` lookback window (7 days). When-to-use and when-to-use-the-other-tool are both covered.

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