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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds non-obvious scope boundaries the annotations cannot convey: no Section 179, no bonus depreciation, no ADS, no dispositions, and not tax advice, plus the fact that results are produced to the cent with PDF/Excel/CSV downloads. It does not discuss pagination or failure modes, but for a pure computation tool that is a minor omission.

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?

It is a single dense paragraph, but the order is well front-loaded: purpose, then optionality, then return values, then exclusions, then the sibling alternative. The long method enumeration is slightly list-like but each item is a genuinely distinct supported mode, so little could be cut without losing selection signal.

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 14-parameter tool with full schema coverage, existing annotations and an output schema, the description supplies what the structured fields cannot: scope, unsupported tax features, required-input minimum, and the sibling boundary. The only residual gap is that it does not flag the conditional requirement of units_total/units_per_year for units-of-production, though the schema descriptions do.

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 would be 3 regardless. The description still adds real meaning by sorting the 14 parameters into a required minimum (cost) versus optional ones with stated defaults (method, life or property class, salvage value, date placed in service), which tells the agent it can call the tool with almost no input. It does not re-explain individual parameter formats, which is appropriate since the schema does that well.

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 verb and resource ('depreciation calculator result for one asset') and enumerates the supported methods (straight-line, 200%/150% declining balance, SYD, units of production, MACRS) plus the property classes covered. It explicitly differentiates from the sibling by restricting scope to a single asset and naming generate_depreciation_schedule for multi-asset cases.

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?

It opens with an explicit when-to-use cue ('Use this when the user wants a depreciation calculator result for one asset') and closes with a when-not-to-use rule plus the alternative tool to use instead. The prerequisites ('Only cost is required') tell the agent the minimum viable invocation, which is strong routing guidance for a 14-parameter tool.

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