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

Annotations only mark it as a non-readOnly, open-world, non-idempotent write; the description adds the material facts an agent actually needs: payment is required via x402 on Solana with a challenge-then-retry flow, invalid targets cost nothing, payloads are never stored, and retests inside 24h are flagged reputation_counted: false. These are behaviors the annotations cannot express.

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 correctly with the verb and payment mechanics, but the middle section is bloated: tier prices are stated twice (the 'Prices (RULED)' line, then again in the 'What the standard $25 includes' paragraph) and item lists are enumerated at length. The content is relevant, yet several sentences could be compressed without losing information.

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?

Despite having no output schema, the description explains what a run produces: a pass/partial/fail verdict with per-dimension summaries, latency, Layer 0 write-back events including a state recommendation on pass only, leaderboard eligibility, and retained digests/call records. Combined with the payment flow and per-tier differences, an agent has everything needed to invoke it correctly.

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 schema already documents all five parameters including tier enum and prices. The description elaborates on tier semantics (prices, retest prerequisite, full-service covering every paid endpoint of a service), but that largely repeats the schema's tier description and says nothing about run_id, seller_ref or endpoint_path. Baseline 3 fits.

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?

Opens with a specific verb+resource+scope: 'Start one paid-and-judged verification run' and immediately describes what the arena does (funds, executes, judges, writes back). This is clearly distinguishable from siblings like arena_quote, arena_eligible and arena_result, which read/price rather than execute a run.

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?

Gives concrete when-to-use conditions: an unknown or ineligible target is answered free before payment, retest requires the same seller to have a prior run of the target, and tier selection is explained. It does not explicitly route the agent to arena_quote or arena_result for pricing/lookup, so the alternatives are implied rather than named.

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