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

With no annotations, the description carries the full burden. It does usefully disclose that the figure is 'rough' and 'non-binding', which sets expectations correctly for a pricing tool, but it says nothing about what happens when location falls outside the metro, whether it errors or assumes KC, or whether a service-area check is a prerequisite.

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 front-loaded sentence with no filler; every qualifier ('rough', 'non-binding', 'recurring commercial', 'Kansas City metro') narrows interpretation. It is tight, though the compactness comes at the cost of the guidance an agent needs before invoking it.

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?

Four parameters, no annotations, and no output schema mean the description must explain what comes back. It does not indicate whether the response is a range, a per-square-foot rate, or a monthly total, nor how the optional location and facility_type alter the result — a meaningful gap for a pricing 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 75% and visits_per_week already has a clear example mapping. The description adds real meaning by constraining location to the KC metro and framing the estimate as recurring commercial work, but it does not explain how facility_type influences pricing or clarify the units of the returned figure versus the per-square-foot request.

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 names the resource precisely: a rough, non-binding cost-per-square-foot estimate for recurring commercial cleaning in the Kansas City metro. It is a noun phrase without a verb, but the scope and output unit are specific enough to separate it from check_service_area, get_service_info, and request_walkthrough.

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 through scope qualifiers (commercial, recurring, KC metro), which implicitly rule out one-time residential jobs or out-of-area requests. However, no when-to-use statement or alternative is named — notably check_service_area, which an agent might reasonably call first in the same workflow.

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