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

Annotations already cover read-only, non-destructive, non-open-world, non-idempotent behavior. The description adds genuinely non-structured context: draws are uniform ('each equally likely'), repeats are excluded by default, and crucially the response is a drawstoday.com link that displays the result rather than containing it. That last point is essential and is not derivable from annotations or schema.

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?

Three tight sentences with the core action front-loaded and the surprising return-format caveat placed before it can mislead. The phrasing 'the answer is a link... the answer itself carries no result' is slightly awkward and redundant, but it earns its place by warning the agent not to expect the drawn values inline.

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?

With no output schema, the description correctly takes on the burden of explaining the return value (a result-page link, not the result). Combined with annotations and the seed documentation, an agent has nearly everything needed to call it. The remaining gap is guidance on distinguishing this from shuffle_list and on what to do with the returned link.

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 only 25% (only `seed` is documented), so the description must compensate. It does: 'list of up to 1000' bounds `items`, 'Pick 1 or more' bounds `count`, and 'Without repeats by default' explains the `unique` default of true. It still never names parameters and omits the 200-character item limit and any interaction between count and list length.

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 and resource with scope: pick 1+ items from a list of up to 1000, equally likely, no repeats by default. An agent immediately knows this is a random subset selection. It does not explicitly differentiate itself from the closest sibling, shuffle_list, which an agent could plausibly confuse with picking multiple items.

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?

Usage is implied by the description (use it to draw a random sample of items), but there is no explicit when-to-use or when-not guidance, and no mention of when to choose shuffle_list, random_integer, or roll_dice instead. The seed sentence in the schema hints at verification use, but the description itself gives no routing guidance.

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