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

Annotations only say destructive=true, idempotent=false; the description adds far more: interdependency rejection (QUESTION_BANK_INTERDEPENDENCY) including draft/live version counting, permanence with no trash/restore, tag cleanup parity with question_bank_tag remove, and draft-vs-live item semantics. This is exactly the extra context the annotations cannot convey.

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?

Front-loads the target distinction and keeps every sentence informative, but it is a single very long run-on paragraph with dense nested clauses that would be easier to parse split by target. No filler, but structure could be improved.

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 3-parameter destructive tool with no output schema, it covers failure modes, permanence, interdependencies, access requirements, and cross-tool behavior. An agent has everything needed to invoke it correctly and to predict consequences.

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%, so the baseline is 3, but the description adds conditional semantics beyond the schema: what each target value actually removes, what questionBankItemId touches, and the rejection rule for public template ids. The schema already covers the required-for-item/rejected-for-bank contract, so this is additive rather than essential.

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 (deletes) and resource (question bank or one item), and immediately disambiguates the two modes via the 'target' parameter. It also asserts exclusivity ('nothing else deletes either'), which lets an agent distinguish it from sibling mutators like question_bank_discard_changes or question_bank_manage.

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 routes to alternatives: publish purges a live item, discard_changes restores a draft-only deletion, duplicate is used for templates instead of delete. It also names a prerequisite reading (riddle://reference/question-bank/overview) and the access doc. When-to-use and when-not-to-use are both covered.

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