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

With only terse annotations, the description carries real weight here and delivers: it explains the 2-of-3 majority mechanism, the per-clue rate limit, and that the tool reads back the ruling ('says what was heard'). That is exactly the kind of non-obvious behavior — a stateful, non-idempotent status change with a quota — that annotations alone (readOnlyHint=false, idempotentHint=false) 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 tightly packed sentences, front-loaded with the core action and effect, then the constraint, then the mode-specific variant. No sentence is filler — each one adds a rule or a behavior the agent could otherwise get wrong.

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 two-parameter mutation with no output schema, the definition covers what the tool does, what changes, and the rate limit. Minor gaps remain: it doesn't say what happens if there is no prior ruling or the per-clue attempt is already spent (error vs. no-op), which matters for an operator with destructiveHint=false but a real state effect.

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 100%, so both parameters (slug, play_id) are already documented in the schema, including that play_id comes from start_story. The description adds no further parameter meaning, so the baseline 3 applies; the phrase 'the last ruling' implies how play_id is scoped but does not say it explicitly.

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 description names a specific verb ('challenges') and a specific resource ('the last trivia ruling'), and describes the outcome mechanic (three models judge, ruling flips on 2-of-3). It also distinguishes a second mode — timeline games re-check the last placement — so an agent can tell this apart from game_answer or check_accusation without opening the schema.

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 condition for use is clear (dispute the most recent ruling) and a hard constraint is stated explicitly ('Once per clue'), which prevents repeat-call mistakes. It stops short of naming the sibling an agent should call instead when the goal isn't to dispute a ruling (e.g. answering again via game_answer), so it does not reach a 5.

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