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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety and self-containment are covered. The description adds genuine behavioral context the annotations do not: the exact deterministic formula chain (Table I flow, Table II tank minimums, Table III loading rates) so the agent knows the output is a rule-derived minimum, not an estimate. It does not disclose failure behavior for unsupported inputs.

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 three outputs and the regulatory basis in the first sentence, then spends the rest on the formula, which is dense but load-bearing for this tool. Every sentence earns its place; only the footnote/page references are slightly verbose for an agent.

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, so the description correctly enumerates the three return quantities (tank gallons, pump tank gallons, drainfield area). Inputs, defaults, and the computation path are all covered. Minor gap: output units for drainfield area (sq ft) and any input-validation limits are not stated.

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 100% with defaults and enums documented, so the baseline is 3. The description adds real meaning beyond the schema: bedrooms and building_sqft both feed a 'larger of' design-flow calculation (with the stepwise gpd tiers), while soil and drainfield select the Table III loading rate used as the divisor. That mapping is not derivable from the schema alone.

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+resource (compute minimum septic tank size, pump tank size, and drainfield area) and pins the scope to a single-family home under Florida Rule 62-6.008. Even among 40+ calc_* siblings, the regulatory domain and the three returned quantities make it uniquely identifiable.

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 scopes usage clearly ('for a single-family home under Florida Rule 62-6.008'), which tells the agent when this rule set applies, including the jurisdictional limit. It stops short of naming exclusions (commercial systems, non-Florida jurisdictions, soil types outside the three enum values) or pointing to an alternative tool.

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