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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds the fullness factor range (1.5-3.0x) and the return concept, but for a pure calculator that is modest added context beyond what structured data provides.

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 core computation, short sentences, no filler. It reads slightly choppy and mixes input/return/sibling notes, but overall efficient and appropriately sized for a simple calculator.

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, the return need not be explained, and the description covers the purpose, inputs, and a cross-reference. It is adequate for a two-parameter calculator, the only gap being the conflicting unit/type statements versus the schema.

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 schema documents both parameters, but the description actively misaligns with it: it says 'window width m' while the schema field is window_cm in centimeters, and calls fullness a numeric 'ratio (1.5-3.0x)' while the schema defines it as a string enum (flat/standard/generous). This introduces unit and type confusion rather than adding meaning.

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 ('Compute total curtain width') with the domain qualifier 'window dressing'. It hints at related calculators but does not disambiguate from the close sibling calculate_curtain_fabric, which is arguably the most relevant alternative.

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 window dressing' gives implied context, and it points to list_bundles for related tools. However, it never addresses when to use this versus the near-identical calculate_curtain_fabric or calculate_fabric_needed siblings, leaving real disambiguation to inference.

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