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

Annotations already convey that the tool is read-only, idempotent, and non-destructive. The description adds behavioral context by noting that it screens for wet-cleaning safety and provides conservative estimates. This clarifies that the tool is for planning and safety assessment rather than execution, even though it doesn't detail how unsafe combinations are handled.

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 description is a single, front-loaded sentence that packs key information without unnecessary words. It lists both inputs and output categories efficiently. While a slightly more structured breakdown could improve readability, the description remains concise and to the point.

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 conveys the general plan structure (safety assessment plus estimates of labor, chemistry, equipment, drying, and steps), but it lacks specifics on how parameters influence results, how to handle unknown codes or materials, or the output format. Given the tool's complexity, the description provides an adequate but not fully complete picture.

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 description coverage is only 9%, placing the burden on the description to explain parameters. The description mentions four inputs (furniture, care code, material, soil level) but does not add meaningful semantics for the other seven parameters (workers, petSpots, stainType, hasDryVacuum, hasExtractor, looseCushions, itemCount). The mapping helps but is insufficient for a tool with 11 parameters.

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 clearly identifies the tool's function as screening wet-cleaning safety and estimating labor, chemistry, equipment, drying, and steps for upholstery cleaning. The specific verbs 'screen' and 'estimate' combined with the resource 'upholstery' distinguish it from other planning tools like carpet cleaning or water damage cleanup.

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?

The description implies the appropriate use case: planning DIY upholstery cleaning when furniture type, manufacturer care code, material, and soil level are known. It does not explicitly exclude carpet or water damage scenarios, but the focus on upholstery makes the context clear. No alternative tools are mentioned, though the resource specificity provides sufficient guidance.

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