bootstrap_curve

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: the echoed request is fully RESOLVED, indices from build_curve results are added automatically, identical duplicates are collapsed, and conflicting ids are rejected. It omits side-effect/persistence information (whether bootstrapped curves are stored on the engine) and auth/error behavior, keeping it short of a 5.

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 single-line purpose is front-loaded, followed by a scannable Args block and a short response note, so an agent can extract the essentials quickly. Density is high and RST-style quoting adds minor noise, but no sentence is filler given the 0% schema coverage.

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 an output schema existing (which would excuse omitting return values), the description still explains the resolved request echo, the per-curve summary fields, and where sampled values live, closing the loop for the caller. Gaps remain around persistence, error semantics, and engine-version gating beyond the one calendar_overrides note, but for a six-parameter nested-reference tool this is close to complete.

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 0%, so the Args block is doing all the work, and it documents every one of the six parameters with types, formats (YYYY-MM-DD for as_of), accepted union forms, and cross-tool provenance references (TermStructure, build_curve results, CurveQuerySpec, build_query results). It also adds semantics the schema cannot express, such as automatic index inclusion and duplicate/conflict handling.

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 opening sentence names a specific verb+resource pair ('Bootstrap curves on the engine and sample them') and pins the HTTP endpoint, so the agent knows this both constructs and evaluates curves. It implicitly separates from build_curve / build_value_curve by accepting their outputs as inputs, but never explicitly names a sibling it is not, so it falls short of full sibling differentiation.

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?

Usage is conveyed indirectly through the accepted input types: curves may be TermStructure objects, build_curve results, or session references, which tells the agent this is the sampling step downstream of build_curve/build_query. There is no explicit when-to-use vs when-not, and no routing language against bootstrap_inflation_curve or sample_vol_surface, so guidance remains implied.

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