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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's value-add is the data-currency contract: prices reflect the account's tier, an hour delay otherwise, and a note instead of numbers with no key. That degraded-mode behavior is exactly the kind of thing an agent cannot infer from annotations. It doesn't mention pagination or point count, but for a fixed-length curve that's minor.

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?

A single dense sentence that front-loads what the tool returns and its span, then the data-currency caveat. Nothing is padding, though the trailing 'and a note instead of numbers without one' is syntactically compressed enough to require a second read.

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 zero-required-param read tool with full schema coverage and no output schema, the description gives the resource, its span, granularity, and freshness behavior — enough to call it correctly. What's absent is return shape detail (number of tenors, missing-data representation), a modest gap given no output schema exists.

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% and the `fresh` parameter's description already spells out the live view, 5-credit cost, free-where-already-live case, and no-op without a key. The description only restates the freshness/account-tier context at a higher level, adding framing but no semantics beyond the schema; baseline 3 applies.

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 verb+resource ('the whole US Treasury curve in one call') and bounds the scope concretely to 3M bill through 30Y bond with daily closes, which separates it from series-oriented siblings like get_series and get_yield_closes. It does not explicitly name or contrast with get_curve_history or get_rates_and_curve, which is why it stops short of 5.

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 implied by 'in one call' — the agent can infer this is the bulk/whole-curve option rather than a per-series call — but no when-to-use or when-not guidance is given. With three plausible siblings (get_curve_history, get_rates_and_curve, get_yield_closes) the missing routing rule is a real gap.

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