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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered. The description adds essentially no behavioral context (no error behavior for unsupported units, no precision/rounding note), and its unit list includes 'ft-lb', which the schema enum does not support — a misleading claim rather than added transparency.

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?

Three short sentences, front-loaded with the capability before the use cases. However 'Returns: {input}.' is a malformed placeholder that consumes space without conveying anything, and an output schema already exists.

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?

Unit scope, a usage hint, and a pointer to list_bundles cover the essentials, and the output schema handles return values. The inaccuracy of listing ft-lb as convertible leaves an agent without a reliable view of accepted inputs.

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% with enums on 'from' and 'to', so the baseline would be 3; 'Inputs: value, from, to' merely restates the schema. Worse, the advertised unit set (J, kJ, cal, kcal, kWh, BTU, eV, ft-lb) conflicts with the actual enum (cal, kcal, j, kj, kwh, btu, ev), which could cause an agent to pass an invalid unit.

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 ('Convert energy') and enumerates the supported units, which meaningfully separates it from the many other convert_* siblings (convert_pressure, convert_angle, convert_weight). It does not name a sibling to differentiate against, keeping it short of a 5.

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?

'Use for nutrition, electricity, science' gives domain context but no when-to-use vs. alternatives condition and no exclusions. It also fails to say how this differs from calculate_energy_physics or calculate_kinetic_energy, which are adjacent energy tools in the sibling list.

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