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

Annotations already declare readOnly, non-destructive, non-idempotent and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: uniform probability per item, an explicit cap of 1000, and the default no-repeat behavior — the latter also explaining why the operation is not idempotent.

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 zero filler, front-loading the core action and following immediately with the probability and uniqueness semantics. Nothing could be cut without losing information.

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 4-parameter tool with no output schema, the description covers the selection semantics but omits edge cases an agent would want: what happens when count exceeds the number of usable unique items, and whether duplicate values in the input are tolerated. Adequate but not fully complete.

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 partially: '1 or more' maps to count's minimum, 'up to 1000' maps to the maximum, and 'without repeats by default' explains unique's default of true. However it says nothing about seeding/reproducibility (left to the schema) or the per-item length limit, so gaps remain.

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?

Names a specific verb and resource ('Pick 1 or more items from a list') plus scope ('up to 1000') and the selection guarantee ('each equally likely'). It is distinguishable from roll_dice/flip_coin/random_integer, but never contrasts itself with the closest sibling, shuffle_list, which also operates on a list.

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?

There is no when-to-use or when-not guidance and no alternative is named. The reader must infer that this is the tool for sampling a subset, whereas shuffle_list reorders the whole list. Usage is only implied by the verb.

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