Skip to main content
Glama

questionBank_delete

Destructive

Deletes a question bank and every one of its items. Rejected with a QUESTION_BANK_INTERDEPENDENCY error if a Riddle in this bank's own project still references it, and BOTH VERSIONS OF A RIDDLE COUNT: the reference tracking is refreshed on every write - a publish, a duplicate, a template-use, an edit in the Creator, or a draft edit through the Builder API (riddle_builder_update and the riddle_builder_* tools) - and it looks at the draft AND, while the Riddle is published, at the live version. So adding a QuestionBank block pointing at this id is enough to protect the bank without (re)publishing, and removing that block from the draft of a published Riddle does NOT release it: the live version keeps pulling the bank until the Riddle is republished or unpublished. A successful delete therefore does mean no Riddle in the project references the bank. Two things the guard still does not cover: a validate-only call (riddle_builder_validate) writes nothing and so registers no reference, and the guard is scoped to this bank's OWN project. If the delete IS rejected, find the referencing Riddles with riddle_list/riddle_get, then either remove the QuestionBank block or repoint it at a different bank via riddle_builder_update - questionBank_riddleBlockItems can preview a specific block you already found. Irreversible once it succeeds. Tags the bank carried are cleaned up like questionBank_removeTag does it: one that nothing else uses any more is deleted from the project, one a Riddle or another bank still uses stays. Rejected for a public template id, see questionBank_templateList.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionBankIdYesThe ID of the question bank to delete.

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the destructiveHint annotation, it discloses cascade deletion, irreversibility, tag cleanup semantics, and the nuance that live versions may keep references until republish. This gives the agent operating expectations far 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.

Conciseness4/5

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

The text is front-loaded with the core action and the critical irreversibility/tag cleanup behavior. It is verbose in the middle with a dense dependency-tracking explanation, but most of that detail is genuinely actionable for a tool as destructive as this one.

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

Completeness5/5

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

For a single-parameter delete tool with no output schema, this covers the main outcome, rejection causes, cleanup effects, exceptions, scope limitations, and remediation. Nothing an agent needs to call it correctly is missing.

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?

The schema already covers the sole required parameter at 100%, so the baseline is 3. The description adds useful semantic caveats, namely that public template IDs are rejected and that the bank must be free of Riddle references, which helps the agent understand what questionBankId values are valid.

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?

It opens with 'Deletes a question bank and every one of its items,' which is a specific verb plus a clear resource and scope. This also differentiates it naturally from sibling tools like questionBank_deleteItem.

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?

It gives concrete conditions for rejection, explicitly tells the agent to find referencing Riddles with riddle_list/riddle_get, and prescribes remediation via riddle_builder_update. It also names questionBank_templateList for the public-template rejection case, giving clear alternative routes.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation4/5

Tools are largely distinct by name and detailed descriptions, with clear prefixes (riddle_builder_*, questionBank_*, stats_*). Some potential confusion exists among the stats tools (stats_fetch vs stats_overview_fetch vs breakdowns) but descriptions clarify their different scopes. Overall, an agent can usually pick the right tool.

Naming Consistency4/5

Naming follows a predictable prefix+verb pattern within each domain (e.g., riddle_builder_quiz, riddle_builder_poll; riddle_get, riddle_publish). Minor inconsistencies exist, like the camelCase 'questionBank' and 'riddleTemplate' prefixes vs snake_case elsewhere, and 'stats_overview_fetch' ordering, but these are not chaotic and remain readable.

Tool Count1/5

With 62 tools, this far exceeds the recommended 3-15 range and even the 25+ threshold. While the server covers a broad domain, the extreme number overwhelms and makes tool selection harder, fitting the 'extreme mismatch' criterion for 50+ tools.

Completeness5/5

The tool surface is exceptionally comprehensive, covering creation, reading, updating, deleting, publishing, unpublishing, moving, tagging, template management, question banks, palettes, and various stats breakdowns. There are no obvious gaps in the lifecycle of managing interactive content, and all apparent operations are supported.

Resources