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

Annotations already declare this is a non-read-only, non-destructive, open-world write. The description adds substantial behavioral context on top: default visibility is public, "private" scopes it to the cook, passing only changed fields creates a partial fork, and a repeated identical change returns the existing version (already_existed) rather than duplicating. Minor tension: that dedup behavior reads as idempotent while idempotentHint is false, though the disclosure itself is accurate and useful to the agent.

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?

Front-loaded with the core action and tightly packed — nearly every clause carries a rule an agent needs. The single dense paragraph mixes several distinct policies (confirmation, visibility, dedup, refusal), which costs some scannability but wastes little.

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?

Covers the full decision surface for a mutation tool of this complexity: prerequisites, confirmation discipline, partial-vs-full list semantics, default visibility, dedup outcome, and the sibling to use instead. An output schema exists, so return-shape explanation is correctly left out.

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?

At 50% schema coverage the description compensates on the highest-risk semantics: partial saves are allowed, but ingredients and steps, if supplied, must be the complete new list, and the fork is auto-named unless title is passed. It leaves several fields (servings, cook_minutes, prep_minutes, tags, seasons, chef_note, author, yield_label) to the schema, which documents most of them, so the gap is modest rather than critical.

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: saves the cook's own version of someone else's recipe, linked to the original, with the original left unchanged. It also explicitly distinguishes itself from update_recipe and notes that this tool refuses on the cook's own recipe, so an agent can pick between the two 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 concrete trigger utterances ("make it dairy-free and keep that", "halve the sugar", "save it for 8"), a prerequisite step (get_recipe first and edit it), a mandatory confirmation gate (show the changes, get a yes, never save silently), and the explicit alternative for the opposite case (update_recipe).

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