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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the description's job is to add context beyond that safety profile. "Side effect: appends a probe turn" does exactly that — it tells the agent the call mutates match state cumulatively while remaining non-destructive. It doesn't mention the arena key/auth requirement beyond what the schema says, keeping it from a 5.

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 WHEN and differentiation clauses are front-loaded and every sentence carries routing information; the worked example at the end is useful. Slightly penalized for the redundant leading tool-name repetition and the telegraphic, punctuation-dense style.

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?

With an output schema present the description needn't explain return values, and annotations plus a fully described schema cover the rest. It supplies the role, the side effect, and the sibling routing needed to invoke it correctly; only auth/key handling and probe-count limits are left implicit.

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 the baseline is 3; the schema already documents key, message, and match_id including where the match id comes from. The description only repeats the parameter names in a worked example and adds no semantics (message length, format, probing strategy) beyond the schema.

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 gives a specific verb and resource ("send one conversational probe toward the hidden token") plus the role constraint ("as attacker"), and explicitly names the siblings it is not (colosseum_claim, colosseum_defend, colosseum_enter). An agent can distinguish this from the other colosseum_* tools without opening any schema. The leading name repetition is redundant but harmless.

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?

A WHEN clause states the exact situation for use, and three alternatives are named with the condition that selects each (final guess with 2 max, defender seat, open match). This is explicit when/when-not/alternative guidance, not inference.

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