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

Annotations already cover the safe-read profile (readOnlyHint true, destructiveHint false, openWorldHint false, idempotent). The description adds genuinely new behavior: it enforces method refusals, cites HSE/UK guidance and Control of Lead at Work duties, and discloses that `urgency` is returned only when paint has already been disturbed unsafely. It does not describe the shape of the remaining response, which matters since no output schema exists.

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?

Purpose and method policy are front-loaded and the worked example is compact and useful. The body is one long multi-clause sentence that packs judging, method screening, guidance and return behavior together, which is dense but not padded.

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 10-parameter, zero-required, read-only advisory tool with a nested trade object and no output schema, the description covers the decision logic, the method policy and the conditional urgency return well enough to call it correctly. It leaves the overall response structure and the role of the trade profile unaddressed, so it is not fully complete.

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 60%, but the description compensates with real meaning: planned_methods values are classified into refused vs permitted-with-care, already_disturbed is tied to the conditional urgency output, and the example shows how build_year, surfaces, planned_methods and the child/pregnancy flag combine. `trade`, `era`, `original_paint_likely` and `children_under_6_or_pregnant` are not explained beyond their schema text.

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 a specific function (judging lead-paint risk from build year, surfaces, condition and test results) plus the downstream output (safe removal, clean-up and waste steps, CLAW duties). It is clearly distinguishable from siblings like paint_quantity and prep_checklist because it is a risk assessment, not a calculator or checklist.

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?

Use is implied strongly by the input shape and by the explicit method policy (dry sanding, blowlamps and dry scraping refused; wet abrading, chemical strippers and heat guns below ~450 C allowed with care), which tells the agent both when to call and what it will do with planned_methods. It never explicitly says when not to use it or names a sibling alternative such as prep_checklist, so it stops short of a 5.

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