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

Annotations already declare readOnlyHint, idempotentHint, closed-world, and non-destructive, so safety is covered. The description still adds meaningful behavior the annotations do not: results are a bounded snapshot of retained data (implying truncation or retention limits) and repeated scheduling is discouraged without operator sign-off. That is genuine value beyond the structured fields, though it stops short of saying how fresh or how large the snapshot is.

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 with no filler, and the core read scope is front-loaded before the operational caution. Nothing is padded, though the extreme brevity leaves terms like 'bounded' and 'retained' undefined.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. Still, for a polling-style tool in a crowded poll-tool family, the description omits what distinguishes it from get_poll and gives no meaning to its one parameter, leaving real gaps.

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?

There is a single optional 'category' parameter with 0% schema description coverage, so the schema offers no meaning at all. The description never mentions category, its accepted values, or nil semantics, so it fails to compensate for the coverage gap; an agent has no basis for deciding whether or how to supply it.

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 supplies a verb ('Read') and a resource ('retained public questions'), which is more than a restatement of the name, but 'bounded snapshot of retained public questions' is opaque about what an 'update' actually is. With siblings like get_poll, get_poll_examples, and get_poll_format in the same family, the description never distinguishes this tool's payload from theirs, leaving the agent to guess.

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 sentence 'Only schedule repeated checks on explicit operator request' is a real usage constraint that steers the agent away from unsolicited polling. However, there is no positive guidance on when to call this versus get_poll, and no stated preconditions or exclusions beyond the polling caution.

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