Riddle

question_bank_delete

Destructive

Deletes a question bank or ONE of its items - "target" says which, and nothing else deletes either. target "bank" removes the bank and every item it holds (its tags cleaned up exactly as question_bank_tag(action: "remove") does), and is rejected with QUESTION_BANK_INTERDEPENDENCY while a Riddle of the bank's own project still references it - counting the DRAFT and, on a published Riddle, the live version too, so a block removed from a draft does not release the bank until that Riddle is republished; read "deletingABank" in riddle://reference/question-bank/overview before deleting one. target "item" takes questionBankItemId and touches nothing else: on a never-published item the delete is immediate and permanent, on a published one it only leaves the DRAFT - a live Riddle keeps drawing that item until question_bank_manage(action: "publish") purges it, and question_bank_discard_changes brings it back until then. Both are permanent for the caller: there is no trash and no restore. Rejected for a public template id - a template is copied with question_bank_manage(action: "duplicate"), never deleted.

Input Schema

TableJSON Schema

Name	Required	Description
`target`	Yes	What to delete: "bank" (the bank itself and every item in it) or "item" (one question of it).
`questionBankId`	Yes	The ID of the question bank to delete, or of the bank the item belongs to.
`questionBankItemId`	No	The ID of the item to delete, as returned by question_bank_get_items or question_bank_item(action: "add"). Required for target "item", rejected for "bank".

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

AddedSep 2, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only say destructiveHint=true, so the description carries the full burden — and it delivers: permanence with 'no trash and no restore', the QUESTION_BANK_INTERDEPENDENCY rejection while a Riddle (draft or live) references the bank, tag cleanup matching question_bank_tag(action: "remove"), and the subtle draft-only deletion for published items until a publish puрges them. No contradiction with annotations; in fact the permanence details amplify the destructiveHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core routing — that target selects bank vs item — is front-loaded, and every sentence carries load-bearing information about errors, permanence, or recovery paths. The cost is a single ~250-word paragraph with heavily nested clauses that is genuinely hard to parse; breaking it into per-target sections would earn a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a high-complexity destructive operation with no output schema, the description covers nearly all decision-relevant edges: interdependency, draft/live semantics, template rejection, tag cleanup, and a reference pointer. Minor gaps: the success response is never characterized, ownership/permission requirements are only implied by 'for the caller', and the error code 'QUESTION_BANK_INTERDEPENDENCY' appears possibly misspelled.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, setting a baseline of 3. The description adds meaning beyond the schema by explaining the behavioral consequences of each target value, the 'touches nothing else' guarantee for questionBankItemId, its state-dependent behavior (never-published vs published), and the dual role of questionBankId as either the bank to delete or the parent of the item.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: 'Deletes a question bank or ONE of its items - target says which', and immediately asserts 'nothing else deletes either', which distinguishes this tool from every sibling that manipulates banks/items without deleting them. The two explicit modes (bank vs item) leave no ambiguity about the tool's scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use and when-not-to-use guidance: the interdependency rejection condition, the draft-vs-live distinction for published items, and the hard exclusion 'Rejected for a public template id - a template is copied with question_bank_manage(action: "duplicate"), never delected'. Names the alternatives that complement it (question_bank_manage publish to purge, question_bank_discard_changes to recover) and points to a reference document. Nothing is left to inference.

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

All Riddle tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool is scoped to a distinct resource/action area: media, palettes, projects, question banks, Riddles, templates, tags, stats, and support. Potentially close pairs like riddle_tag/riddle_tag_delete and question_bank_delete/question_bank_manage are cleanly separated by their descriptions, so an agent can reliably select the right one.

Naming Consistency4/5

The naming is mostly consistent snake_case with strong resource prefixes like riddle_, question_bank_, and template_, followed by clear verbs. Minor deviations such as question_bank_item, riddle_tag, and stats_fetch break the strict verb-noun pattern but remain predictable once the convention is understood.

Tool Count3/5

At 38 tools this is a heavy surface, though the breadth is justified by the many subdomains the server covers: media, palettes, projects, question banks, Riddles, templates, tags, and stats. Most tools earn their place, but the count sits above the range where an agent can quickly survey all options.

Completeness4/5

The set covers the full lifecycle for Riddles, question banks, templates, and tags, including publish/unpublish, move, stats, and media upload/delete. Minor gaps like no media library listing and read-only project settings are workable because media IDs come from upload responses and project permissions are exposed.

Resources

Need Help?