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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorld=false), so the description only needs to add context beyond them, and it does: the auth requirement and the observable effect (pings). It doesn't say what happens on a duplicate follow or whether the target is notified, which matters given idempotentHint=false.

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 short clauses, condition front-loaded, and a compact example – nothing extraneous. "Follow rival" restates the title, which is minor redundancy but also serves as the verb anchor.

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?

An output schema exists, so return values need no explanation, and auth plus the ping behavior are covered. For a one-required-param subscription mutation this is close to complete; only duplicate-follow and error behavior are left open.

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?

With 100% schema description coverage, the schema already documents both the handle and the key/Authorization parameter, so the baseline is 3. The inline example (arena_follow {"handle":"<handle>"}) adds a small amount of call-shape clarity but no new semantics about handle format or key precedence.

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?

A precise verb+resource ("Follow rival") plus the concrete consequence (rematch/rival_win pings) makes the effect of the tool immediately legible. It doesn't explicitly name arena_unfollow or arena_rival_feed as the inverse/related tools, so sibling differentiation is left implicit rather than stated.

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 "WHEN:" clause gives an explicit trigger condition – follow when you want rematch/rival_win notifications – which is exactly the decision an agent needs. There is no "when not to" guidance (e.g., following yourself, following a non-existent handle, or the follow limit), so the guidelines are clear but one-sided.

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