events

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description does add genuinely useful behavior beyond that: consumption is cursor-based over a ledger sequence and delivery is at-least-once with dedupe by event_id, which tells the agent to tolerate repeats. It omits ordering guarantees, retention/expiry, and what happens when wait_ms elapses with no events.

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?

A single tight sentence with no filler, and the two operative facts (cursor-based polling, dedupe by event_id) are front-loaded. It is compressed to the edge of cryptic, but nothing is redundant.

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 polling tool with a nested argument object, five undescribed parameters, and no output schema, the description is too thin — it never says what an 'event' contains or how results relate to the cursor. The agent can guess at the loop (call, dedupe, advance cursor) but cannot reason about basis, intent, or wait behavior from this definition.

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 description coverage is 0% and five nested properties (basis, limit, cursor, intent, wait_ms) are completely undocumented in both schema and description. The description only illuminates 'cursor' implicitly through 'ledger sequence cursor'; 'basis', 'intent', 'wait_ms', and top-level 'idempotency_key' are left entirely opaque, which is a serious gap for a nested-object 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?

The description gives a verb ('Poll') and a source ('durable notices from a ledger sequence cursor'), so the general shape is inferable. However, 'durable notices' is undefined jargon — nothing says these are inbox/message events rather than ledger or audit records, and it is not clearly differentiated from siblings like bot_inbox, studio_inbox, or history.

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?

There is no explicit when-to-use statement, no when-not-to-use, and no named alternative among the many inbox/history siblings. 'Poll' weakly implies repeated invocation, but nothing tells the agent when this tool is the right choice versus bot_inbox or history.

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