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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the description correctly spends its words elsewhere: it discloses that a calculation receipt (inputs, results, assumptions, validation checks, source) is returned and that the receipt is unsigned and not independent certification. It also rules out external lookup, private data and code execution. The only gap is the lack of detail on what validation checks can fail and how failures are reported.

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?

Purpose and capability are front-loaded in the first two sentences, and the caveats about receipts and temperature/money exclusions follow in a logical order. A few sentences restate what the schema already enforces (required 'inputs' wrapper, exact enum choices), which is defensible as error prevention but slightly redundant. The style is choppy but each sentence carries information.

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 an output schema present and rich annotations, the description covers the remaining essentials: the two modes, the receipt's trust status, and the domain exclusions. What is missing is guidance on how the dimensions mode is composed (unit+power pairs) and on temperature-difference handling, which is the least self-evident part of the schema. Overall it is sufficient for an agent to call the tool correctly in the common case.

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 reported as 0%, so the description carries more burden than usual. It does clarify the wrapper contract ('Put tool fields inside inputs', 'Supply units or modelVersion only when listed in inputSchema', 'Do not pass the REST calculator field'), which is genuinely useful beyond the schema. But it never explains the dimensions-mode parameters (left/right arrays, power exponents, the 8-item cap) or the distinction between absolute and delta temperature units, leaving the more complex branch unexplained.

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 opening sentence names a specific verb (convert) and enumerates the exact resource domain (length, area, volume, mass, time, speed, force, pressure, energy, power, temperature, angle), then names the second capability (dimensional checks of two explicit products). The 'without evaluating arbitrary formulas' clause separates it from general math/formula siblings like buscalc_linear_algebra or buscalc_business_data_calculations.

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 gives real selection context: use this for unit conversion or dimension comparison, not for arbitrary formula evaluation. It also states hard exclusions ('money conversion is unavailable', 'offset temperatures are forbidden in products'), which is stronger than most siblings. It does not, however, name an alternative tool for the cases it refuses, so it falls short of a 5.

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