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

Annotations already declare readOnly, idempotent and closed-world, so safety is covered. The description adds genuinely useful framing beyond that: results are indicative and not legal/financial advice, and the maker is named, which helps an agent caveat output correctly.

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?

Front-loads the verb, resource and scoping axes, then supports with examples. The trailing provenance/disclaimer sentences are useful but slightly padded, keeping it just under maximally tight.

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?

No output schema exists, and the description does signal that both ABSD and BSD figures come back and that they are indicative. All three parameters are documented at 100% coverage, so an agent has what it needs, with only the precise return shape left implicit.

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 100%, so the baseline is 3. The description earns above baseline by tying profile/propertiesOwned combinations to concrete rate outcomes (20% for SC second property, 5% for PR first), adding interpretive meaning the raw enum does not carry.

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 (calculate) and resource (ABSD plus BSD) and the exact scoping axes (buyer profile, number of properties owned). It also implicitly distinguishes itself from the sibling calculate_bsd by noting it returns both ABSD and BSD.

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 two worked examples (SC second property = 20%, PR first = 5%) clarify the context in which each profile/property combination applies, giving the agent concrete usage signal. It stops short of explicitly stating when to prefer calculate_bsd or calculate_ssd instead, so no full 5.

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