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

Annotations already declare readOnly=false, idempotent=false, destructive=false. Beyond that, the description adds real behavioral context: the state transition from local to public and a validation constraint (question count limit and tariff-restricted question types). It does not cover re-publishing behavior or reversibility, but the annotation coverage lowers the bar.

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?

Two tightly written sentences with the core effect front-loaded and the precondition second. Every clause carries information; no filler.

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 publish action, the agent learns what changes (local becomes public) and the gating precondition. No output schema or annotations gap leaves it nearly sufficient, though it is silent on how this interacts with existing published versions, which get_quiz_versions implies may exist.

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% with a single parameter, so the schema fully documents quiz_id. The description adds no syntax or format detail beyond the schema, so the baseline of 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 states a specific verb and resource ('Публикует опрос') and clarifies the exact effect: the current local version becomes public. This is distinct from siblings like archive_quiz, create_quiz, or restore_quiz, though it does not name-check any sibling to sharpen the distinction.

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?

Usage is implied by the effect: use when a local draft should go live. It adds a precondition (the draft must fit the tariff), but names no alternatives (e.g. restore_quiz, set_share_link_active) and gives no explicit when-not guidance.

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