rx_send_for_approval

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

Annotations already declare readOnlyHint=false and idempotentHint=false, so the mutation profile is known. The description adds genuinely useful context beyond that: it creates and starts a task, it mutates RX data, it never signs the document, and it hard-fails when no approval rule exists.

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?

Front-loaded with purpose, then modes, then caveats, then the pre-call workflow instruction. Every sentence carries information, though the mode explanation partially duplicates the schema's own mode description.

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 six-parameter mutation tool with no output schema, the description covers the important decision points: mode choice, rule absence failure, signing exclusion, and the confirmation workflow. It does not say what the call returns (e.g., a task id), which is a minor gap given there is no output schema.

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 every parameter is already documented in the schema (mode, deadline, approver_ids, signatory_id, document_id). The description largely restates the mode semantics already present in the schema field, adding little beyond what the structured data provides. Baseline 3 is appropriate.

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 ('Отправить документ на согласование: создаёт и стартует задачу') and draws an explicit negative boundary ('Подпись документа этот инструмент не ставит'), which separates it from signing flows. The two mode behaviors further pin down what actually happens.

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?

Explains when each mode applies (free = named people and deadline; rule = route built by the RX regulation) and adds a failure condition ('если правила нет, RX откажет'). It also gives a workflow precondition ('перед вызовом перескажите пользователю...'). It does not, however, route the agent away from near siblings such as rx_send_for_acquaintance, so no explicit alternative is named.

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