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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real value: it discloses the methodology (BLS OEWS median wage for SOC 43-4171, ECEC benefits excluding paid leave because those hours are already inside 2,080, NCS leave days, JOLTS quits times a replacement-cost share) and a price-check date. That lets the agent judge output trustworthiness, though it says nothing about units of the return value beyond 'monthly cost'.

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?

The core purpose is front-loaded in the opening clause and every parenthetical (wage series, benefit exclusions, leave, replacement-cost share) earns its place as provenance. It is a single dense sentence whose length is justified but is harder to scan than it needs to be, and the URL could be trimmed.

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 params, no output schema and read-only annotations, the description supplies the methodology and the comparative framing an agent needs to call it correctly. What is missing is any hint of the shape of the returned comparison (per-option cost figures, assumptions echoed back), which would help the agent interpret results.

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 interpretation: hours_per_week changes the model from a full-time hire to covering N hours a week, and the comparison is held at the same call volume. It does not explain the calls default of 150 or the effect of state on which wage series is used, so it is not a full 5.

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?

The description states precisely what the tool computes: monthly cost of an in-house receptionist versus the cheapest AI/virtual receptionist at the same call volume, with named data sources. It is unambiguous as a cost-comparison calculator, but it never names or distinguishes itself from siblings such as compare_at_volume or get_vendor_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?

There is no explicit when-to-use or when-not guidance, and no alternative is named despite an obvious overlap with compare_at_volume and get_vendor_pricing. The only orientation is the implicit 'one full-time hire or N hours a week' mode, which is left for the agent to infer.

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