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

Adds substantial behavior beyond the annotations: the legal state machine, the 409 failure mode, the auto-advance clock (hostSecs per question, 8 s per answer reveal), and how pause/resume and manual steps interact with that clock. It also discloses the organizer-key auth requirement, which the annotations (only readOnly/destructive/idempotent/openWorld) do not cover.

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?

Front-loaded with the action list, then tight sentences on ordering, timing, and auth — every clause carries information. The only waste is the opening clause duplicating the title almost verbatim.

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 non-idempotent mutation tool with no output schema, the description covers auth, legal ordering, failure codes, and timing side effects, which is nearly everything an agent needs. It omits any indication of what a successful call returns, a minor gap given no output schema exists.

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 50% — slug is documented in the schema but the action enum is not. The description compensates by spelling out the body shape and describing what pause/resume actually do to the clock, giving real meaning to two enum values the schema leaves bare.

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 ('Run a live quiz') and enumerates the exact state transitions it performs (start, reveal, next, finish, pause/resume). No sibling tool in the list does this, so an agent can distinguish it immediately from get_dashboard, get_results, or update_settings.

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 concrete applicability conditions: only for quizzes with host = true, and it requires the organizer key. It also specifies the legal call ordering (lobby → question → reveal → … → done) and that anything else returns 409. It does not name an alternative tool for the non-host case, but the gating condition is explicit.

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