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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower. The description adds genuinely new behavior: accepting immediately starts the bout, and wins award no LOB — a consequence an agent needs before committing. It doesn't explain what happens on a failed/duplicate accept, which would complete the picture.

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?

Four short sentences, front-loaded with the action and eligibility, then the consequence. 'fighter is your fighter' is slightly redundant against a 100%-documented schema but is not wasteful enough to hurt.

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 only two well-documented parameters and no output schema, the missing pieces are limited to failure modes and return shape. The description covers eligibility and the post-accept consequence, which is most of what an agent needs to call it safely.

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 100% and both parameters carry descriptions, including the fighter enum, so the schema does the heavy lifting. The description's 'fighter is your fighter' merely restates the schema rather than adding format or selection guidance (e.g. how to obtain a valid match_id).

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 ('Accept ... challenge') and narrows scope to open challenges or ones addressed to you, which separates it from arena_challenge (creating) and arena_get (reading). It stops short of naming a sibling explicitly, so an agent must infer the boundary from the arena_* family names.

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 tells you what kinds of challenges qualify ('open' or 'addressed to you'), which is implied usage context. It never says when to prefer this over arena_challenge, arena_rematch, or find_matches, and gives no prerequisites for accepting.

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