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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false), the description discloses the resolution method (17 county rolls, Texas franchise registry, mailing addresses, name roots), the exception clauses consulted, and the exact return payload including a stored screening_id — consistent with a non-read-only call. It omits any statement about permissions, latency, or what happens on re-runs with the same order_id.

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?

Two dense sentences with the action front-loaded and the mechanics packed into parentheses; every clause carries information. The long parenthetical about statutory citations is heavy but appropriate for a compliance tool.

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 complex, 15-parameter regulatory screen with no output schema, the description does the important work: it names all four decision outcomes plus penalty exposure, control chain and screening_id, so the agent knows what comes back. The gap is on the input side, where most optional parameters are left unexplained.

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 only 20% (buyer, contract_date, claimed_exception), so the description must compensate; it partly does by naming the specific exception clauses (36.5–36.11) that populate claimed_exception and by noting the property and seller are read from the roll, implying those inputs are optional. The remaining eleven parameters — price, county, co_date, order_id, buyer_zip, parcel_id, year_built, closing_date, property_zip, buyer_address, property_address — get no explanation anywhere.

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?

States a specific verb and resource ("Screen a single-family home purchase (a title order)") and immediately scopes it to the ROAD Act institutional-investor ban, which cleanly separates it from siblings like who_owns_home, road_investor_group and road_purchase_stream.

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 makes the screening context clear and enumerates the exception regimes it evaluates, so an agent can infer when to call it. It never states when NOT to use it, nor does it route the agent to obvious alternatives such as who_owns_home (ownership lookup) or road_investor_group (control-group exploration) when a full screening is not needed.

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