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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the key behavior the annotations cannot express: this is a soft delete with a 30-day trash retention and a recovery route. It does not state permission requirements or what happens if the recipe is already gone, which keeps it short of a 5.

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 zero filler; the usage restriction is front-loaded before the behavioral detail. Every sentence carries information the 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 single-parameter destructive tool, the description covers the essentials: when to call it, that it is reversible for 30 days, and how to reverse it. What remains unstated is edge-case behavior such as deleting an already-trashed or nonexistent recipe, which is minor but not nothing.

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% and the single recipeId parameter is already documented with type, pattern, and max length in the schema. The description adds no format or sourcing detail (e.g., where to obtain the id) beyond what the schema provides, 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 ('delete a saved recipe'), names the affected library, and distinguishes the operation from its recovery counterpart restore_recipe. An agent can differentiate it from siblings like save_recipe or remove_recipe_from_cookbook without opening the 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?

Explicitly gates invocation on 'the user clearly asks to delete a saved recipe', which is a real exclusion criterion for a destructive action. It also names the alternative path (restore_recipe) and the window in which it applies.

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