build_value_curve

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

With no annotations, the description carries the full burden and delivers substantive behavior: it will not hit the engine, the curve is anchored at the first point, discount requires the first point to be the reference date with value 1.0, forward supports only Linear/BackwardFlat/ForwardFlat, and compounding/frequency apply only to zero points. It omits the mutation/side-effect profile, e.g. whether the curve is registered under id in the session or whether an id collision overwrites.

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?

Purpose is front-loaded in one sentence, then a tight Args block where nearly every line adds unique semantics. The market_data_source entry is long but each of its four values changes agent behavior, so it earns its space.

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?

For a 10-parameter, enum-heavy builder with no annotations, the description supplies conventions, defaults, cross-parameter constraints and a return shape. The remaining gap is statefulness — whether id registers the curve in the session and how duplicates are handled — which matters for a tool whose output includes a curve handle.

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 coverage is 0% (only titles, no per-property descriptions), so the description must compensate and does: it documents id, kind semantics per enum value, point syntax with a concrete example, reference_date format, the preset-vs-conventions choice, compounding/frequency scope and defaults, and interpolator defaults per kind. This is richer than the schema.

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 first sentence names a concrete verb and resource ('interpolated curve from explicit values') and adds the discriminating clause 'no engine call', which separates it from engine-driven builders. It never names its closest siblings (build_curve, bootstrap_curve, curve_from_pasted_table), so the agent must infer the boundary itself.

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?

It gives a clear when-not rule ('If you would have to invent numbers, do not call this tool: ask the user for the data') and defines the four market_data_source situations that license a call. What it lacks is routing between siblings — nothing says when to prefer this over build_curve or curve_from_pasted_table.

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