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

The description asserts 'Повторный вызов с тем же значением ничего не меняет' — i.e. that repeated identical calls are no-ops — while the annotations declare idempotentHint: false. That directly contradicts the structured hint an agent relies on and would mislead it about re-invocation safety; the genuine value it adds (per-recipient semantics, tariff gating) does not offset the conflict.

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 short sentences, front-loaded with the core action and then the mode meanings and the tariff caveat; there is little filler. Structure is efficient and every clause carries information, though the final idempotency clause is not just wasted but harmful.

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 simple 3-required-parameter write tool with no output schema, the description covers the action, both mode semantics, and a real business constraint (tariff gating), which is enough for an agent to call it. The gap is resource/lifecycle context (its relationship to the email-recipient and email-settings siblings) rather than core behavior.

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 enum values for `type` are already documented in the schema ('owner — письмо автору, client — копия респонденту'). The description only restates that mapping rather than adding syntax, defaults, or constraints (e.g. what happens to `enabled` if the tariff does not permit client mail), so 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+resource ('Включает или выключает письма опроса') and then disambiguates the two modes, owner (author notification on new response) and client (copy to respondent). This is clear and more specific than a bare toggle, but it never names the sibling it must not be confused with (e.g. toggle_quiz_email_recipient), so full sibling differentiation is missing.

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 only implied: the tariff note ('Копия респонденту доступна не на всех тарифах') is a precondition and the repeat-call note is a re-invocation caveat, but there is no explicit when-to-use guidance or routing to an alternative tool (save_quiz_email_template, toggle_quiz_email_recipient, etc.).

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