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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-derivable detail: the recipe 'travels in the link itself and is not stored by ChefSums', which tells the agent about persistence and privacy. The ex-VAT/inc-VAT and default 30% food cost statements are also useful framing, though return-field detail partly duplicates the output schema.

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?

Two sentences, front-loaded with the purpose before the output/environment details. The second sentence is long and semicolon-packed, but every clause carries distinct information (outputs, link behaviour, non-persistence).

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?

Five parameters, a nested ingredient array and a rich annotation set are all covered, and the description explains the one output field (open_in_prepsheet_url) an agent would otherwise have to discover. With an output schema present, return values needn't be spelled out further; only explicit sibling routing is missing.

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%, so the schema already documents portions, pack_price, pack_size, quantity_used and the two percentage defaults. The description reinforces the key constraint ('same unit as the pack size, e.g. grams') but adds no semantics the schema doesn't already carry — baseline 3 is correct.

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?

Opens with a specific verb + resource ('Cost any recipe from its ingredients') and immediately enumerates the outputs (line cost, batch cost, cost per portion, suggested menu price). This is clearly separable from siblings like calculate_gp and build_prep_list without opening any schema.

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 when-to-use is implied by the purpose ('cost a recipe') but no sibling is named and no when/when-not condition is stated — e.g. nothing tells the agent whether to use this or calculate_gp for margin work. The sentence about open_in_prepsheet_url describes a downstream action, not tool selection.

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