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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: offset/limit page a bounded response locally, and private login and prize redemption codes are excluded from results. That exclusion detail is the kind of context annotations cannot convey.

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, front-loaded with what is returned, then the non-selection guarantee, then paging/exclusion behavior. Every sentence contributes distinct information with no filler.

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 usefully discloses what is returned (winners and prize titles) and what is omitted (private login and redemption codes). It could go further on response shape or pagination bounds, but it is sufficient for an agent to call it correctly.

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 0%, so the description must carry the burden, and it does: it maps 'Unix timestamps' to begin_ts/end_ts, 'offset/limit page' to those two params, and 'a promotion's winners' implies promotion_id. It does not state the limit ceiling (100) or default (50), leaving a small 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?

States a specific verb and resource ('Read a promotion's winners and prize titles') that clearly distinguishes it from sibling list tools covering brands, entries, and promotions. The additional clause 'Reads existing winners without selecting new ones' removes any ambiguity about whether this triggers a draw.

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 gives clear usage context: use it to read existing winners, optionally filtered by Unix timestamps, and it explicitly says it does not select new winners. It does not name an alternative sibling tool or state a when-not condition by name, so it falls short of a 5.

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