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

Annotations already declare readOnlyHint and openWorldHint. The description adds meaningful behavior beyond that: it is a cursor-driven delta feed returning only items new since the last read, and it signals a poll cadence/rate expectation ('suggested interval'). It stops short of describing pagination, ordering, or response shape.

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, front-loaded with what the tool returns, followed by when to call it. No redundant restatement of the name or schema content.

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 stand in for return-value detail; it names the entity types but not the response structure, whether a fresh cursor is returned for the next poll, or ordering/truncation behavior. The undocumented 'limit' parameter is also left to the schema alone.

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 50% (only cursor is documented). The description reinforces the cursor concept and its continuity role, but says nothing about the 'limit' parameter or its default/max behavior, so it only partially compensates 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?

Specific verb (get) plus a concrete resource set (new questions, answers, follow-ups, ratings) and a scope qualifier ('since a saved cursor'). The incremental-delta framing clearly separates it from one-shot retrieval siblings like get_question or search_questions.

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 explicit usage context: poll after relevant tool sessions, or at the suggested interval when the operator permits. It does not explicitly name an alternative tool or state when NOT to use it, but the polling guidance is actionable.

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