key_rate_ladder

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

With no annotations, the description carries the full behavioral burden, and it does disclose useful traits: the exact reprice count (1 + 2 + 2 x pillars), concurrent execution bounded by QUANTRA_MAX_CONCURRENCY, and strict market_data_source semantics. It never states side effects or persistence (e.g., that the run is a pure read, or what a 'session' source implies about prior writes), leaving the safety/profile picture incomplete.

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 one-line purpose, then cleanly split into Args and Result sections; the densest material is the market_data_source paragraph, which earns its space as a usage guard. The 'as in swap_dv01' shorthand is efficient, though the result-format sentence is long enough to need rereading.

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 return values need not be restated, yet the description still names the ladder/parallel/sum_of_buckets/definitions/calls fields, and it covers the provenance, curve-selection, and cost-of-call dimensions an agent needs. The remaining gap is the opaque market payload and override object, which neither schema nor description clarifies.

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% across 9 parameters, so the description must compensate. It fully defines market_data_source (all four enum values with provenance meaning), explains curve's default and that buckets are the curve's ACTUAL points in wire order, and defers market/trade/bump_bp/method/as_of to swap_dv01. The market object (open additionalProperties), request_id, and calendar_overrides remain entirely unexplained, so compensation is partial.

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 computation (key-rate DV01 ladder = one bump per curve pillar plus a parallel bump), which is a concrete verb+resource+scope rather than a restated name. The reference to swap_dv01 for shared arguments implicitly positions it as the bucketed counterpart of swap_dv01, but the contrast is not spelled out explicitly.

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 when-not rule tied to data provenance: 'If you would have to invent numbers, do not call this tool: ask the user for the data,' plus the rule that engine_example is only valid when the user asked for an example. It does not, however, say when to choose this over swap_dv01 or scenario.

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