Update recipe

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

Annotations already declare readOnlyHint=false, destructiveHint=true and idempotentHint=true, so the agent knows this is a mutating but idempotent call. The description adds the partial-update semantics that annotations do not express. But with destructiveHint=true and nested steps/ingredients arrays, it never says whether supplying steps replaces the whole list or merges, nor whether omitted fields are preserved—the central risk when calling this tool.

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 short sentences with the key scoping rule (only send fields to change) placed early; no filler or redundancy. It is efficient but undersized for the surface it covers.

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?

This is a 16-parameter destructive update with nested objects, no output schema, and near-zero schema coverage; the description does not come close to carrying the required burden. An agent cannot learn from it how nested arrays behave, what validation applies, or what the response will look like, which matters because no output schema exists to explain returns.

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 only 13% across 16 parameters; only id and format carry inline descriptions. The description's "all fields optional except id" merely restates the required array and adds no meaning for name, steps, nutrition, private, internal, properties, source_url or the timing fields, many of which are nested objects whose merge behavior is undefined.

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: "Update recipe metadata and content." An agent can distinguish it from create_recipe, get_recipe and update_meal_plan without opening a schema. It does not explicitly name which sibling to use when a recipe doesn't yet exist, but the verb makes that near-obvious.

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?

"Only provide fields you want to update" gives partial-update (PATCH-style) guidance, which is genuinely useful. However, there is no when-to-use-vs-alternatives guidance, no mention of prerequisites or permissions, and no statement about whether use create_recipe for new recipes or how to handle conflict with import_recipe_from_url.

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