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

Though annotations already declare destructiveHint=true and idempotentHint=true, the description adds genuinely new context: permanence ('cannot be undone'), the catalogue-recipe safety constraint, and a linked-account requirement. These are exactly the preconditions an agent needs before invoking an irreversible mutation.

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 tight sentences with no repetition: the irreversible nature is front-loaded, then the usage condition, then the two hard constraints. Every sentence carries distinct information.

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?

An output schema exists and annotations cover the safety profile, so the description need only supply the human-facing constraints – irreversibility, catalogue exclusion, and account linkage – all of which are present. Nothing an agent needs before calling is missing.

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 recipeId description already points to list_saved_recipes as the source. The tool description only echoes that the target is one of the user's own recipes, adding no syntax or sourcing detail beyond the schema; 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 ('Permanently deletes one of the user's own saved recipes') and immediately scopes it against siblings by clarifying it applies only to the user's own saved recipes, not catalogue recipes. An agent can distinguish this from update_recipe, get_recipe, or save_recipe without opening any 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 explicit when-to-use guidance ('suits a request where the user has confirmed which recipe to delete') and a clear exclusion ('Catalogue recipes can't be deleted'). It stops short of naming a concrete alternative for non-deletion intents (e.g. update_recipe), which would be needed for a 5.

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