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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false, idempotentHint=false), so the description is not the sole carrier of safety information. It still adds real behavioral context beyond the annotations: unspecified fields are preserved, which tells the agent it can update one setting without clobbering others. It stops short of covering auth needs, side effects of enabling scripts/pixels, or any rate/consistency behavior.

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 sentences total for a 91-parameter tool, with verb+resource front-loaded and the behavioral rule (partial update) placed after the scope list. The domain enumeration is long but functional — it bounds a very large surface — and no sentence is redundant.

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?

Given the tool's size, the description adequately conveys scope plus the key mutation semantic. The remaining gap is modest: with no output schema, it says nothing about what the call returns or how array-valued settings (extra_fields, quiz_categories, available_devices) behave on update versus merge, but return values for a settings updater are largely predictable.

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%, so the schema already documents all 91 parameters, including constraints, enums and cross-field caveats. The description's parenthetical grouping of domains adds orientation but no syntax, format or dependency information beyond what the schema supplies, so the 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?

States a specific verb and resource ('Обновляет настройки опроса') and enumerates the setting domains it covers (display, navigation, limits, captcha, theme, scripts, QR, schedule, analytics, SSO, scoring, etc.), so an agent knows this is the general settings-mutation tool. It does not, however, disambiguate against overlapping siblings such as rename_quiz, apply_quiz_theme, manage_quiz_analytics or manage_quiz_passwords, so an agent may still have to guess which surface owns a given setting.

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 second sentence gives a genuinely useful operational rule ('only the fields to change are passed; the rest are untouched'), which tells the agent this is a partial/PATCH-style update. There is no explicit when-to-use-vs-alternative guidance, no prerequisites (e.g. auth, publish state), and no statement about which sibling tools own the settings that overlap this one.

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