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

The description adds several important behavioral details beyond the annotations: deterministic execution (no AI generation), the 50-question round limit, the persistence of question_N IDs on the first edit, and the 409 stale response for optional source_stage. It does not contradict annotations. It could mention whether questions are appended or replace existing ones, but the disclosed quirks are valuable and non-obvious.

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 sentences, no fluff. The core purpose and key constraints are front-loaded, and the behavioral nuances (ID persistence, staleness) are concisely presented. Every sentence earns its place.

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 mutation tool with nested parameters and no output schema, the description covers the main usage context: deterministic addition, round prerequisites, question limits, and concurrency behavior. It does not describe the response shape or explicitly state whether questions are appended vs. replaced, but the schema and sibling tool names provide enough surrounding structure. Overall, it is adequate with minor gaps.

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 0%, so the description must compensate. It explains the purpose of source_stage (stale check) and the round_id requirement, plus the 50-question limit. However, it leaves parameters like guidance, followUpQuestions, tags, and id without explicit semantics — although their names are self-explanatory, the description does not fully compensate for the zero schema coverage.

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 ('Add') and resource ('questions to one draft round'), immediately distinguishing it from siblings like add_competencies, add_skills, and update_questions. The phrase 'exactly as written' adds precision about the behavior. It is clear what this tool does and how it differs from related tools.

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 states that this is for deterministic, non-AI question addition, implying it is the manual counterpart to generate_questions_directions. It also gives concrete constraints ('Requires rounds', 'at most 50 questions') that indicate preconditions. It does not explicitly name alternative tools or state when not to use it, but the context is clear enough for an agent to choose correctly.

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