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

Annotations already declare write/destructive/idempotent, so the description's real contribution is downstream consequence: the recipe's nutrition, label and cost change. That tells the agent the blast radius beyond the single line. It does not say whether omitted fields are cleared or preserved on a PUT, which is the remaining behavioral unknown.

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 dense clauses: mutation marker and scope first, the hard limitation second, side effects third, endpoint last. No filler and the constraint that matters is front-loaded.

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 mutation with no output schema, the definition covers scope, restrictions, precedence and side effects. The one gap is update semantics for omitted fields, which matters given the PUT-style naming and idempotentHint.

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 every parameter including the total_grams override is already documented. The description restates the field list and precedence rather than adding syntax, defaults or interaction rules the schema lacks. Baseline 3 applies.

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?

Names a specific verb and resource ('change the AMOUNT of one ingredient line in a recipe') and lists the exact mutable fields. It also states what the tool is not ('It cannot swap the ingredient'), which separates it from recipal_add_recipe_ingredient and recipal_remove_recipe_ingredient without opening either 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?

Gives an explicit when-not with a redirect: to swap an ingredient, remove the line and add another. It also supplies the selection rule between parameters ('total_grams overrides unit and quantity'). It stops short of routing against other near siblings such as recipal_scale_recipe or recipal_update_recipe, which an agent must still disambiguate on its own.

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