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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered and a pure calculator needs little more. The description's only added behavioral content is about return values ('Returns selling price and the other metric'), which the output schema already covers, so it adds limited value beyond structured fields.

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 core purpose and the disambiguating 'often confused' note. The trailing 'See list_bundles for related finance-universal calculators' is mildly off-topic for a calculation call but not bloated.

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?

An output schema exists, so return values need not be described, but the description instead states an input contract that contradicts the schema's required parameters (cost + selling_price). For a required-argument calculator this misdescription is a material completeness defect.

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?

The description claims the inputs are 'cost and either markup % or margin %', but the schema requires cost and selling_price and exposes no markup/margin parameters at all. With 100% schema coverage the baseline would be 3, but this stated contract actively conflicts with the schema and would lead an agent to supply a nonexistent parameter.

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 concept ('convert between markup and margin') and even flags the common confusion, so the agent knows exactly what the tool computes. It does not, however, distinguish this from close siblings such as calculate_profit_margin or calculate_cost_price, which handle overlapping pricing math.

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 pricing decisions or COGS reporting' gives a usage context but no when-not guidance and no explicit routing to alternatives despite many competing margin/profit siblings. The pointer to list_bundles is a discovery hint rather than a selection rule, so usage is only implied.

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