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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, so the safety profile is known. The description adds genuinely new behavior: the preview-then-confirm gate for state-changing steps and fail-fast semantics where an errored step stops the run and is reported. Permissions and auth requirements are not covered.

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 sentences that front-load the core action before the preview/confirm caveat and the error behavior. No padding, though the parenthetical '(see recipe_runs)' is a minor aside.

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?

With no output schema, the description responsibly states what comes back (each step's result plus markers_path) and describes failure behavior. A mutation tool with nested params and a confirm gate is adequately covered, though it is silent on what the preview response itself contains.

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 name, params, and confirm are already documented in the schema. The description reinforces confirm's semantics but adds little syntax or format detail beyond what is structured, so the 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?

States a specific verb and resource (executes a recipe end to end) and enumerates the internal phases: binds params, runs each step's tool in order, persists the run. Clearly distinguished from siblings like recipe_list, recipe_get, and recipe_runs.

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-to-use flow: state-changing recipes preview first and require a second call with confirm:true, read-only recipes run immediately. It does not compare against manually invoking the constituent tools, but the conditional invocation guidance is unusually clear.

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