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

Annotations only carry the generic safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false); the description adds substantial non-obvious behavior: the object stays an unannounced draft the host must open in the app, the AI can be wrong so every question must be checked, consent gating on the AI setting, audience rules preventing adults and teens sharing a show, and content screening for teens' groups. This is real context the agent could not infer from the annotations.

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?

The vital information (draft-only, host review, consent gate) is front-loaded in the first sentence, which is good, but the remainder is a dense em-dash run-on packing questions, scoring, access tiers and audience rules into two oversized sentences with no structure. Some length is justified for an 11-kind nested question schema, yet the prose could be broken into scannable clauses.

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 complex 7-parameter tool with nested question objects, an output schema covering return values, and full schema descriptions, the description supplies the domain rules an agent needs — draft semantics, consent, access levels, audience separation, point cap, and the in-app-only question kinds. Nothing material to calling it correctly is left out.

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 100%, so the baseline is 3, but the description still adds constraints not in the schema: 1–30 questions, the 1000-point cap per question, and the fact that picture rounds and the sound question can only be made in the app rather than supplied here. The kind list largely echoes the enum, which caps this below 5.

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 first sentence states a specific verb and resource — drafting a live quiz night — plus the exact scope (a group, household chat or channel the person hosts) and the precondition that it is host-initiated. It also disambiguates from a hypothetical scheduling/announcing action by stating the result is a DRAFT nobody else sees, so no sibling tool can be confused with it.

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?

It gives an explicit trigger ('only when they ask') and an explicit refusal condition ('refused if the person's AI setting for groups is off'), plus the constraint that nothing is scheduled until the host reviews and schedules in the app. What is missing is a named alternative sibling (e.g. list_quiz_shows for resolving 'where', or the app for picture/sound rounds) to route an agent that cannot use this tool.

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