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

With annotations only providing idempotentHint=false, the description carries the full burden and does so excellently. It discloses the draft/publish state transition, the fact that a bank with unpublished changes still draws from the last published state, the delayed purge effect of questionBank_deleteItem, and the rejection for public template ids. This goes well beyond what the sparse annotations provide.

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?

The description is a dense paragraph of 3-4 sentences, but every sentence contributes meaningful behavior: the core publish action, the drawing-from-last-published behavior, the deleteItem purge timing, and the template rejection. It is front-loaded with the main action, though a bit long; the length is justified by the subtle semantics.

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 single-parameter mutation with no output schema and only an idempotency annotation, the description is remarkably complete. It explains the full effect of the operation, the state model, related tools for verification, and an edge case that causes rejection. No critical behavioral aspect is missing for an agent to select and invoke this tool safely.

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 description coverage is 100% and the only parameter, questionBankId, is already documented in the schema as 'The ID of the question bank to publish.' The description adds no additional parameter-level detail, which is acceptable given the schema's clarity. Baseline 3 applies.

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 uses a specific verb ('Publishes') and resource ('question bank') and clearly explains the core action: draft content becomes published content. It distinguishes this from sibling questionBank tools by introducing the draft/publish split and noting the template exception, setting it apart from questionBank_get, questionBank_discardChanges, and questionBank_templateList.

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?

The description implies when to use this tool: when you want to make draft changes live, and it explicitly mentions that questionBank_get shows unpublished changes and that questionBank_templateList covers the template restriction. It lacks a direct 'use this instead of X' statement, but the context is clear and excludes a distinct case (public template ids).

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