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

Annotations already establish a safe, closed-world read operation, so the bar is lower; the description goes further by disclosing the exact formulas, including that bags are rounded up. It does not address the edge case where bag_lb defaults to 0 (division by zero for the bags output), leaving one behavioral ambiguity.

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-loaded with the answer (what you get), followed by a compact formula block that earns its space as an authoritative reference. The first sentence is a long run-on chain, and the formula block partially duplicates the schema semantics, but nothing is wasted.

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 correctly specifies the return values (per-1,000 rate, total, bags, P2O5/K2O), which is essential here. All six params are optional with full schema coverage, so the only shortfall is the undocumented bag_lb=0 behavior.

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%, so the baseline is 3, but the description adds real value by tying parameters to their roles: N rate drives product per 1,000, area drives the total, bag weight drives bag count, and P%/K% drive the phosphate and potash outputs. The one gap is not explaining what happens when bag_lb is left at its default of 0.

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: pounds of product per 1,000 sq ft and for the whole lawn, derived from N rate and N-P-K. It also enumerates the full output set (total product, bags to buy, phosphate and potash applied), which makes it unambiguously distinct from neighbors like calc_grass_seed or calc_sod without opening a schema.

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 opening 'How much fertilizer to put on your lawn' implies the use case, but there is no explicit when-to-use/when-not guidance and no named alternative among the many calc_* siblings. An agent must infer that this is the fertilizer-dosing tool rather than seeding or sod coverage.

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