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

Annotations already declare destructive=true and idempotent=true, so the description's real contribution is the extra context: the permission requirement (owner or admin seats), the side effect that the activity log retains the question text, and the exact idempotency contract (a repeat after deletion returns success). It doesn't cover cascading effects on quiz attempts or the response payload, but it goes well beyond the annotations.

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 compact clauses, front-loaded with the destructive action and permission scope, then the audit-log behavior, then the idempotency instruction. Dense but not wasteful; the phrase "as its Delete does" is slightly awkward but carries real meaning about parity with the UI.

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 destructive, idempotent, two-parameter tool with no output schema, the description covers the critical facts: permanent deletion, authorization, audit retention, and repeat-call behavior. What's missing is the success/failure response shape and whether quiz attempts or results referencing the question are affected, but the essentials for correct invocation are present.

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 50%: idempotency_key is fully documented in the schema, and question_id is a bare UUID. The description reinforces the idempotency_key retry semantics ("Pass the same idempotency_key when retrying"), which is useful but largely duplicates the schema description rather than adding new meaning to question_id.

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 ("Deletes a quiz question") and clarifies the UI parity ("as its Delete does"), so an agent can tell it apart from edit_training_question or archive_training_module. It doesn't explicitly name a sibling alternative, which keeps it just below a 5.

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?

Usage is implied by "deletes outright" (permanent removal vs. editing), and the owner/admin seat restriction narrows when it can be used. However, it never explicitly says when to choose this over edit_training_question or archive_training_module, leaving the agent to infer the alternative.

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