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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real substance. So the description adds real substance: the estimates are built *only* from cited line items, every figure carries its source, and the return contains per-cycle and multi-cycle low, typical, and high values. This tells the agent where the figures come from, but not whether they are cached or updated, and does not address rate limits.

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?

It is a single sentence with no filler, front-loaded on the core claim and followed by the component and output detail. The long nested parenthetical makes it denser than it needs to be, but nothing is wasted.

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 two-parameter, read-only estimator with no output schema, the description carries the return-value burden well by specifying the low, typical, and high figures, their per-cycle and multi-cycle scope, and per-line source attribution. The main omission is a note that figures are national aggregates rather than clinic-specific, which matters given the neighboring clinic-price tool.

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 schema already fully documents both `cycles` and `include`; the description adds only incidental color. Its parenthetical list (medications, anesthesia, embryo freezing, frozen transfer, genetic testing, add-ons) roughly echoes the `include` enum and its default set, and "for several cycles" hints at the `cycles` multiplier, but neither parameter is explained beyond that.

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?

It clearly states what the tool produces (a US IVF cost estimate) and names the exact components and output shape (low, typical, high per cycle and multi-cycle, with a cited source per line). The only gap is that it never distinguishes itself from siblings like find_ivf_clinic_prices, leaving it implicit that this is a generic national model rather than a specific clinic's pricing.

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 only implied by the word "US" and the generic, line-item-based approach; the description never says when to choose this over find_ivf_clinic_prices, ivf_insurance_rules, or employer_ivf_coverage, nor does it state any exclusions. An agent can infer this tool suits ballpark planning, but the inference is not stated anywhere.

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