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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false, openWorldHint). The description goes beyond them by disclosing data provenance (spot/strike/DTE/IV pulled live from Deribit), the semantic intent of the discrepancy metric, and the failure mode ('available: false + error if the instrument name doesn't resolve'). It stops short of stating rate limits or freshness/latency caveats for the live pull.

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 with the core purpose and the trust-check framing, and every clause carries information. The trailing enumeration of return fields is a long run-on list, but given there is no output schema it is mostly earning its place rather than padding.

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?

No output schema exists, and the description compensates by naming the returned fields (instrumentName, currency, optionType, deribitMarkPriceCoin, deribitMarkIvPct, bsPriceCoin, priceDiscrepancyPct, available) and the error path. Combined with clear usage triggers and a 100%-covered schema, an agent has everything needed to call and interpret 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 coverage is 100%, so the parameter documentation burden is already met; the description adds context beyond that by giving a concrete instrument format and clarifying that the name must come from an external options chain. It does not elaborate on riskFreeRatePct semantics, but the schema's default-0 convention note covers that.

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+resource (Black-Scholes theoretical price and Greeks for a live Deribit instrument) and explicitly positions itself against its nearest sibling: 'Returns everything workflow.run_black_scholes does, plus...'. It also names the shape of the answer (priceDiscrepancyPct trust-check), so an agent can distinguish it from both the static BS tool and adjacent option workflows like run_implied_volatility.

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 explicit trigger conditions and quoted user phrasings ('is this option fairly priced?', 'what are the Greeks on this contract?') plus the required precondition that the user supply a specific instrument name. It also states what this tool does NOT do ('this tool does not browse the chain, it prices one named instrument'), which routes the agent away from misuse.

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