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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety behavior is covered. The description adds genuinely useful non-annotation detail: exactly 16 facts, and that each carries value, unit, as_of, a human-readable calc, and a source URL — which matters because no output schema exists. It stops short of stating ordering, error behavior, or what an empty filter match returns.

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 identity, then the fact inventory, then when-to-use, then filtering. The long enumeration sentence of fact families is dense but each item is informative; the only slack is minor redundancy between the fact list and the later 'several figures at once' phrasing.

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?

With zero required parameters, no output schema, and full annotation coverage, the description supplies the two things an agent would otherwise lack: the shape of each returned record (value, unit, as_of, calc, source URL) and the fact inventory. Nothing needed to call it correctly or interpret the response is missing.

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 baseline is 3, but the description adds selection semantics beyond the schema: id is exact and comma-separated, q is a substring match on the label, the two are alternatives rather than combinable filters, and passing nothing returns all 16. That default/all-results behavior is the main value added over 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?

States a specific resource (16 pre-computed sourced facts) and enumerates precisely what those numbers cover: index/sub-index levels, structure premium, universe size, spread range, peak maturity, N-PORT coverage, CoreWeave repricing, and NCSX vs US HY OAS. This is concrete enough that an agent can distinguish it from ncsx_index, ncsx_curve, or ncsx_latest without opening any schema.

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 selection criteria: use it when the user wants a number to cite, a comparison, or several figures at once, and explicitly contrasts that with stitching five endpoints together. It lacks named sibling routing (e.g., 'for raw time series use ncsx_curve instead'), so it is clear context without hard exclusions.

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