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

With no annotations provided, the description carries the full burden of behavioral disclosure. It communicates the calculation types, the optional density-driven outputs, and the basis behavior, which is solid for a pure calculator. It does not describe the return format or state that inputs are validated, but it does not need to discuss side effects or destructive behavior for this kind of tool.

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?

The description is compact and front-loaded: it states the formula source first, then the mode behaviors, then the optional basis behavior. Every sentence contributes either mode guidance, output behavior, or default context, with no filler or repetition.

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 an 8-parameter, 3-mode tool with no output schema and no annotations, the description covers the main behavioral surface well: modes, basis, formula source, and optional outputs. The main gap is that the 'max' mode is only implied via 'Optional Gb' rather than explicitly linked to the schema's mode='max' value, and required parameters per mode are left to the schema descriptions.

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 75%, and the description adds semantic grouping that the raw schema lacks: wet+dry masses map to sample mode, start/target MC maps to drying mode, and Gb maps to MCmax/MCsink. It does not enumerate every parameter, but the schema already documents each one, and the description clarifies how the parameters relate to the modes.

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 clearly identifies the domain (wood moisture content) and gives specific mode semantics: sample-based MC_od/MC_wb from wet+dry masses, and drying outcome with mass/water lost. It distinguishes itself from sibling calculators like wood_emc and wood_shrinkage by its explicit formula reference and mode breakdown. However, it says 'Two modes' while the schema exposes three mode values, and it never explicitly names the 'max' mode, which slightly weakens precision.

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 gives clear usage context by explaining the two primary computation modes, the optional Gb-based MCmax/MCsink output, and the od/wb basis with od noted as the industry default. It does not explicitly mention alternative sibling tools or exclusion conditions, so it stops short of full routing guidance, but the mode descriptions are enough for an agent to pick the right invocation path.

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