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

With annotations already covering readOnly/idempotent/non-destructive, the description goes well beyond them: it explains the long-poll hold semantics and 30s cap, the cursor-as-ack contract, the exact condition that triggers redelivery ('when the pair changes, events that were served but never acked come back with redelivered: true'), and the credential rule. That is precisely the operational context an agent cannot infer from the annotations.

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?

Purpose is front-loaded in the first sentence, and the dense material (polling loop, ack, redelivery, credentials) is ordered by what a caller needs next. It runs long for a tool description, and the webhook parenthetical and the event-envelope enumeration are partly covered by the output schema, but almost every sentence carries operational weight.

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 9-parameter, stateful, long-polling tool this covers the full picture: invocation pattern, ack/redelivery failure modes, auth options, and event shape. With an output schema present, the envelope description is a bonus rather than a gap-filler, and nothing an agent needs to call this correctly is absent.

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 100%, so the baseline is 3, but the description adds real meaning on top: it explains why `consumer_id` must be durable, how `cursor` functions as an acknowledgement rather than just an offset, and the coupled semantics of `client_instance` + `client_started` (per-boot token pair triggering redelivery). These relationships are not expressible in the flat schema.

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 and resource — long-polling an agent's event feed — and frames it against the webhook alternative ('an agent on stdio MCP cannot host one, so it waits here instead'). That contrast makes the tool's niche immediately legible. It stops short of differentiating from the closest sibling, ledger_alerts, so an agent comparing the two gets no help from this text.

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?

Gives concrete operating instructions: call in a loop, hold up to `timeout` (max 30), reuse a stable `consumer_id`, pass the returned `cursor` back as the ack, and opt into `client_instance`/`client_started` for restart redelivery. What's missing is when-not-to-use guidance or a named alternative among siblings (e.g. ledger_alerts) for the non-polling case.

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