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

Annotations only declare a non-read-only, non-destructive, closed-world mutation. The description adds what annotations cannot: a one-shot idempotency rule, a 30-minute expiry window, dependence on a token from a prior submit_request call, and the exact set of outcome messages ('уже добавлены', 'ничего не добавлено', 'время вышло'). Nothing here contradicts the annotations.

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?

Four tight sentences, front-loaded with the caller restriction, which is the most decision-relevant fact. The enumerated response strings are slightly list-heavy but each conveys a distinct terminal state an agent must interpret.

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?

With no output schema, the description compensates by enumerating every possible response. Combined with the caller restriction and validity window, an agent has everything needed to decide not to call it and to interpret the result if surfaced.

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 the `d` pass, enum values, and maxLengths all documented in the schema itself, so baseline is 3. The description reinforces that `d` comes from submit_request's response and is delivered to the card rather than the model, but adds no field-level detail beyond that.

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?

Names a specific verb and resource ('дописывает детали к заявке') and ties it to the sibling tool that creates the request ('которую только что создал submit_request'), so an agent can distinguish it from submit_request at a glance. It also states outright who invokes it ('Вызывается только формой карточки... Модель этот инструмент не вызывает').

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 explicit preconditions: only from the card form, only for the request just created by submit_request, only once, and within 30 minutes. It also states the negative case for the current caller ('Модель этот инструмент не вызывает'), which is exactly the routing decision an agent needs.

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