Is Arbitrage Profitable

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

Annotations provide the full safety profile (readOnly=true, idempotent=true, openWorld=true, destructive=false), so with annotations the description only needs to add extra context. It adds that the result is free and reflects a 'right now' snapshot of profitability, which gives some dynamic-data context beyond the static hints. It doesn't disclose data sources, caching, calculation logic, or any rate limits, but with the safety profile fully covered by annotations, a with annotations result of 3 is approach the bar.

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 short and the key question is front-loaded, but it packs redundancy: 'Free:' and 'No subscription needed' say the same thing. A cleaner structure—'Check whether PJM vs MISO arbitrage is profitable right now — no subscription required'—would remove the overlapping value statements and keep the same meaning. It doesn't waste sentences, but the promotional duplication carries no new 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?

Given there are 0 parameters, a given output schema, and annotations already carrying the safety/dynamic-traits profile, the description covers what an agent needs to invoke it and interpret the answer to the profitability question. The only small gap is the advanced distinction from sibling pricing-facing tools, but the free-access hint covers enough.

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?

The tool has 0 parameters and schema coverage is 100%, so the baseline is 4 — the description doesn't need to explain parameters. It adds no parameter semantics but none are required; the description quickly points out there are no inputs are needed ('free' and no subscription imply an zero-friction call). For a 0-param tool, the description does not need to compensate for anything.

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 the precise resource (PJM vs MISO arbitrage) and the question it answers ('is it profitable right now'), which is more specific than the tool name alone. The 'Free' prefix is salesy and the question form is not ideal, but the intent is unambiguous enough for an agent to know what the tool does.

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?

'No subscription needed' implies a use case: you can call this without being on a plan, which distinguishes it from subscription-centric siblings like build_subscription_tx and get_subscription_cost. However, it does not explicitly say when to prefer this over get_telemetry or get_oracle_status, nor does it state any conditions or exclusions. Usage guidance is inferred, not stated.

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