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

Annotations already flag destructiveHint=true, idempotentHint=true and readOnlyHint=false, but the description adds the crucial detail annotations cannot express: the operation is reversible through the undo returned in the answer, except for a dinner time, prep days, or date-range rules. It also discloses the failure case (national defaults cannot be deleted) and a human-confirmation precondition, which is exactly the behavioral context a destructive tool needs.

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 sentences, front-loaded with the action and its scope, then exclusions, then the confirm/undo caveat — a sensible ordering with no filler. It loses a point because the undo clause is grammatically muddled ('the answer's undo files the rule again, except a dinner time, the prep days or a rule over a range of dates'), forcing the reader to re-parse what is and isn't reversible.

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 one-parameter destructive tool with no output schema, the description covers the essentials: valid id source, invalid-id class, confirmation, and reversibility exceptions. It does not spell out what the response contains beyond the undo reference or what happens if the rule is already gone, though idempotentHint=true mitigates the latter.

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 parameter already carries 'The rule's id, as get_rules shows it', so the baseline is 3. The description goes beyond the schema by constraining which ids are valid — household-owned rules only, never national defaults — which tells the agent something the schema does not.

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?

The description names a specific verb and resource ('Delete ... meal rules') and bounds the scope precisely: only 'the household's own' rules, identified by 'the id get_rules shows', while national defaults 'are not rules of the household's own and cannot be deleted'. That scope statement separates it from the get_rules sibling and from the upsert_*_rule creation tools without ambiguity.

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?

It tells the agent where the id comes from ('get_rules shows') and imposes a confirmation requirement ('Ask the member first'), which is actionable usage guidance. It stops short of explicitly naming the alternative action for non-deletion cases (e.g., modifying a rule via upsert_category_on_day_rule or set_dinner_time), so the routing guidance is clear but not exhaustive.

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