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

With no annotations, the description carries the full behavioral burden. It discloses that hidden verbs never appear until both seats commit, and mentions full deterministic replays. It also signals 'FREE' and 'Public' implying no auth. However, it does not describe return format, error handling, or whether the view is a snapshot or streaming.

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 description is two sentences, front-loaded with the core purpose, and every sentence adds value (live view contents, hidden verb behavior, replay availability). No fluff or repetition.

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?

While an output schema is present (likely covering return values), the description fails to explain match_id semantics, which is critical for a single-parameter tool. It also omits behavior for finished matches or invalid IDs. However, it does mention replay availability, partially compensating.

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 0% and the description provides no explanation of match_id beyond its use in the replay URL. The agent is not told what match_id represents, how to obtain it, or its format. This is a significant gap given the tool has only one parameter.

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 states a specific action ('Public spectate view of a live BLADE PIT duel') and lists concrete data points (HP bars, range, exchange number, committed flags, revealed verbs, taunts). It clearly differentiates from sibling tools like aiarena_bladepit_queue and aiarena_bladepit_register by emphasizing viewing rather than participating.

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 description implies usage: to watch a live duel, use this tool. It mentions replays via a separate GET endpoint, hinting at an alternative for past matches. However, it does not explicitly state when not to use this tool or name alternatives, though the sibling context makes the distinction obvious.

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