aiarena_bluffduel_spectate

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

With no annotations provided, the description carries the burden and does meaningful work: it declares access is public and free, and it explicitly warns that hidden rolls never appear until an exchange resolves — a non-obvious information-hiding behavior an agent could otherwise misreport. It does not cover polling/freshness expectations, behavior on an invalid or finished match_id, or whether repeated calls return snapshots.

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 access tag and purpose, then the returned fields, then the state-hiding caveat, then the replay fallback — a sensible information ordering. Every sentence carries content, though the unseparated run-on of listed fields makes it marginally denser than needed.

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 one-parameter read tool with no output schema and no annotations, the description covers what is returned, what is withheld, cost/access, and an alternative for replays. The remaining gap is operational: nothing about the ID's provenance or how fresh the snapshot is when polled.

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% for the single match_id parameter, so the description must compensate. It only indirectly conveys meaning by embedding {match_id} in the replay URL template, implying a match identifier reusable across endpoints; it never states the expected format or where the ID comes from (register/queue responses). Partial compensation, not full.

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: a public spectate view of a live BLUFFDUEL dice duel. It then enumerates exactly what is visible (dice counts per seat, bid history, turn indicator, revealed exchanges after LIAR calls), which separates it from the register/queue siblings and from the other game namespaces (bladepit, covenant, century) in the tool list.

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 word 'Public' plus 'live' establishes the use case: watching an in-progress duel without joining or authenticating. The closing pointer to the replay endpoint implicitly tells the agent this tool is not the way to retrieve finished matches. It stops short of an explicit when-not or a named call to a sibling spectate tool, so it is clear context rather than full routing guidance.

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