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

Adds substantial behavior beyond the annotations: nothing is created until a human clicks Create, the link requires a human check, and the follow-up management path is spelled out. This human-in-the-loop constraint is the single most important thing to know and annotations alone would not convey it. Consistent with readOnlyHint=true.

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 sentences, front-loaded with the core action and outcome, no filler. The closing organizer URL is slightly tangential to invoking the tool but is a legitimate handoff note.

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 13-parameter draft tool with no output schema, the description explains what is produced (a link), what the link contains, what the recipient must do, and what happens next. Remaining gaps (validation behavior, error cases) are minor and largely covered by the schema.

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 77%, and the description's field list ('name, entries or questions, rules, closing time, look') supplies natural-language meaning for several of the undocumented params (title, entries/questions, theme, closesAt). It stops short of syntax or format detail, so it complements rather than replaces the schema.

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 precise verb and artifact: 'Make a link that opens QRvote's create form already filled in', and lists what the link pre-fills. It implicitly but clearly separates itself from the sibling create_contest by stating 'Nothing is created until they do' — the agent knows this drafts, not creates.

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 clear usage context: hand the link to a person who checks it and clicks Create, and points to the organizer endpoint for subsequent management. It does not explicitly name create_contest as the alternative for programmatic creation, so the when-not case is only implied.

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