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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds real behavioral context beyond that: deterministic math matching a public calculator, single-performance-obligation scope, and explicit limits (not for multi-element or variable contracts). It does not describe error behavior for invalid model/parameter combinations.

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 action and output shape, then model semantics, then a scope caveat. Dense but nearly every clause carries information. The long parenthetical model list is a single sentence, which slightly hurts scannability but avoids padding.

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 no output schema, the description takes on the burden of return semantics and does so by naming the four monthly columns. It also bounds the domain (single performance obligation) and covers all three models. It leaves the actual response shape and unit conventions implicit.

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 already 90%, so 3 would be the baseline; the description goes further by giving computation semantics the schema lacks, e.g. how billing frequency interacts with the subscription model, that partial months use their own days, and that usage overage is billed monthly with breakage at expiry. It does not restate per-parameter constraints.

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?

Names a specific verb+resource (build a revenue recognition schedule), states the accounting standard (ASC 606 / IFRS 15), the granularity (month-by-month), and the exact output columns (billed, recognized, deferred, unbilled). This is clearly distinguishable from every sibling, all of which are invoice/PO-oriented utilities.

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 strong model-selection guidance by explaining when each of the three models applies (subscription = equal per month with partial first/last; milestone = recognized on delivery, optional deposit; usage = prepaid draw-down with overage and breakage). It also states when-not-to-use via the accountant caveat for multi-element/variable contracts. It stops short of naming sibling alternatives (e.g., calculate_proration) for the partial-period cases.

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