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

Annotations already declare destructiveHint=true, non-idempotent, and write access, so the safety profile is covered. The description adds non-obvious downstream effects — the change alters the recipe's nutrition, label, and cost — plus the precedence rule that total_grams overrides unit and quantity. It is silent on duplicate-line behavior, which matters for a non-idempotent write.

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?

One front-loaded sentence with a tightly scoped parenthetical, followed by the endpoint. Every clause (write marker, unit sourcing, override rule, downstream effects, path) carries information an agent needs.

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 a 6-parameter write with no output schema, the description covers purpose, valid value sourcing, override semantics, and downstream impact. The only meaningful gap is what happens on a duplicate ingredient line, which is relevant given the non-idempotent annotation.

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 all six parameters are already documented. The description contributes the cross-parameter precedence rule (total_grams overrides unit and quantity) and directs the agent to where valid unit values come from, which the schema does not state; otherwise the parameter guidance is schema-duplicated.

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 an explicit verb+resource+scope: 'WRITE: add an ingredient line to a recipe.' The sibling set contains update_recipe_ingredient and remove_recipe_ingredient, and this phrasing makes clear it appends a new line rather than modifying or deleting one.

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?

It gives two distinct calling modes (by unit/quantity vs. total_grams) and routes the agent to the right reader tools to obtain valid units ('see units_and_grams from recipal_get_recipe_ingredient or valid_units from recipal_get_ingredient'). It does not say when to prefer this over recipal_update_recipe_ingredient or what to do if the ingredient is already on the recipe.

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