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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the bar is lower. The description still adds genuine value by disclosing the ordering/no-skip guarantee even under out-of-order commits, which is a real correctness property an agent needs to trust cursor resumption.

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 tight sentences, no waste, and the core action (poll with cursor) is front-loaded ahead of the ordering rationale.

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 no-required-param polling tool with no output schema, the description supplies the essential semantics: what it is, how to resume, and the ordering guarantee. It stops short of describing event shape or how a poller detects it has drained the stream, which is a minor remaining gap.

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 baseline is 3. The description goes beyond per-field docs by explaining the causal link between the cursor and ordering correctness ('a poller resuming from the cursor never skips an event'), which adds cross-parameter meaning the schema alone doesn't convey.

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 ('Poll') plus a clearly scoped resource ('my events (outbox)') and the mechanism ('with a cursor'). This is easily distinguished from siblings like list_messages or list_transactions, though it never explicitly names an alternative.

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?

The description implies the polling flow (resume from cursor, no skips) but gives no explicit when-to-use, when-not, or migration guidance. The 'since' deprecation is only mentioned in the schema, not the description, so usage is left to inference.

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