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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful context beyond that: block_ms is accepted but capped at 0, so despite the "wait" name the call returns immediately with current events. That disclosure prevents an agent from expecting blocking behavior.

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?

Two short sentences, front-loaded with the action and immediately followed by the most surprising behavioral fact. No wasted words.

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 and 0% schema coverage, so the description should describe the return shape and cursor semantics. It conveys that current events are returned but says nothing about what those events look like or how cursor advances, leaving a real gap for a polling tool.

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% across 3 params, so the description must compensate. It does explain block_ms semantics (capped at 0, effectively a no-op), but cursor and inbox_id are left completely undocumented, and cursor is the key pagination parameter for a polling tool.

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 verb and resource ("Poll an inbox"), but it calls the tool "poll" while a sibling is literally named inbox.poll, so it fails to differentiate this tool from that one. An agent cannot tell from the description why it would choose inbox.wait over inbox.poll.

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?

No guidance on when to use this versus inbox.poll, or how the returned events relate to inbox.ack. The only usage-ish statement is that block_ms is a no-op, which is behavior, not routing guidance.

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