price_swaption

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

With no annotations, the description carries the full burden and does substantial work: it explains that settlement_type Physical derives the method from the preset while Cash requires settlement_method, that 'spot' effective_date is engine-resolved via preset settlement days, that built surfaces are wrapped in SwaptionVolSpec with the preset's swap_index_id, and what include_details/include_diagnostics add. It still omits what the market dict must contain and any failure/reversibility behavior.

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?

Structured as a compact, dense Args list where each line addresses a distinct parameter or behavior; little is wasted. It is not front-loaded with a usage summary and the inline cross-references (engine enum names, preset block names) make it long, but the density is justified by a 20-parameter tool.

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 the brief mention of summary.swaptions (npv, implied_volatility, atm_forward, annuity) is sufficient. For a tool at this complexity, though, leaving three required inputs (market, discounting_curve, forwarding_curve) entirely unexplained is an incompleteness an agent will notice at call time.

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?

Top-level schema description coverage is 0%, so the description must compensate, and it does explain roughly half the arguments well (market_data_source, preset, underlying, exercise_date(s), vol, model, include_details, include_diagnostics). But required arguments such as market, discounting_curve, forwarding_curve and as_of, plus additional_trades and calendar_overrides, are never described, leaving significant gaps.

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 ('Price a swaption') plus the underlying endpoint. Against a sibling list containing price_vanilla_swap, price_cap_floor and calibrate_swaption_vol, an agent can immediately tell this is the swaption *pricing* (not calibration) tool.

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 an explicit exclusion: 'If you would have to invent numbers, do not call this tool: ask the user for the data,' and constrains engine_example to 'only when the user explicitly asked to run an example.' However, it never routes to the obvious alternatives (calibrate_swaption_vol, calibrate_swaption_model, price_vanilla_swap) or states prerequisites like a stored market being required first.

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