Поставить задачу

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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, so the write profile is partly covered. The description still adds valuable context: it explicitly warns that it 'Изменяет данные в CRM' and prescribes a show-and-confirm consent flow before writing, which the annotations do not express. Return format and idempotency remain undisclosed.

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, no filler, and the purpose is front-loaded ahead of the operational warning. The consent clause earns its place by guarding a mutation, so nothing reads as padding.

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?

No output schema exists, so the description should ideally cover the required inputs and the write's effect. It handles the mutation-confirmation angle well but omits the two required parameters (text, due) and the entity linkage fields, and the deal/leads terminology clash leaves the target entity ambiguous for a 6-parameter write tool.

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 coverage is only 33%, so the description carries significant burden. It does add meaning for 'срок' and 'ответственный' and maps examples to task types, but it says 'сделке' (deal) while the entity_type enum offers 'leads/contacts/companies' — a mismatch that could mislead — and never mentions entity_id or the required 'text' parameter. Baseline 3 for a schema-led definition is generous here.

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 ('Ставит задачу по сделке, контакту или компании') and enriches it with concrete task examples (перезвонить, отправить КП, встреча) plus the key scope fields (срок, ответственный). It is clearly a task-creation tool, though it never names the sibling it differs from (e.g. crm_complete_task for closing tasks, crm_tasks for listing), so full differentiation is left to inference.

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 only usage instruction is the mutation-confirmation step ('покажите пользователю, что будет записано, и получите согласие'), which tells the agent how to invoke it safely but not when to prefer it over alternatives like crm_complete_task or crm_add_note. Usage context is implied by the entity types mentioned rather than explicitly scoped.

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