save_question

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

With no annotations, the description carries the full burden, and it does disclose one meaningful behavior: the server rejects duplicates and wrong answer positions, and the agent should fix and resend. It also specifies the post-save output behavior (show only the question + reply format). It is silent on other side effects, what persists, and whether the call is idempotent across the 10 optional params.

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?

Roughly five tight sentences with the workflow step front-loaded and no filler. Dense phrasing and the mixed instruction/definition sentences cost a little readability, but nothing is wasted.

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?

A 14-parameter mutation tool with no annotations, no output schema, and 0% schema coverage is the maximum-burden case, and more than half the parameters remain undefined. The description also doesn't state what a successful save returns or how the saved question relates to the pending-question flow, so an agent must guess at several inputs.

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% across 14 params, so the description must compensate. It adds genuine meaning for concept ('2-6 word tag of the single idea tested'), correct_answer ('readable answer text'), key_points ('what a good free-text answer contains'), and the answer_key/required_answer_key match constraint — but leaves hint, subtopic, explanation, review_id, session_id, material_id, and user_id entirely unexplained in both places.

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 and resource ('store the question you wrote') and positions it in the ASK workflow as step 2, which implicitly separates it from get_next_question_brief (step 1) and check_answer/record_result. It stops short of naming a sibling explicitly, so the differentiation is inferential rather than stated.

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?

Gives real workflow context: take topics/qtype from the brief, place the answer where the brief required, then show the user ONLY the question plus reply format. That is clear sequencing guidance, though it never says when not to call it or names the alternative tool for the step-1/step-3 actions.

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