Очистить память ИИ о диалоге

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

Annotations declare a non-read-only but non-destructive, non-idempotent mutation, and the description usefully explains why: only the AI summary is removed, the correspondence persists, and the summary is regenerated from that history. This discloses exactly what is destroyed and what survives, adding real value beyond the annotation flags, though it says nothing about auth or limits.

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 compact sentences with no waste. The primary effect is front-loaded in the first sentence, and the clarifying consequence follows.

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 two-parameter mutation with no output schema, the description plus annotations give an agent enough to call it correctly and understand the outcome. Minor gaps (no explicit precondition or sibling routing) keep it short of complete.

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 both 'case' and 'dialog' fully documented (including fallback behavior for 'case'), so the schema carries the parameter burden. The description adds no further parameter meaning, making the baseline 3 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 – deletes the AI summary for a dialog – so the action is immediately clear. It does not explicitly contrast itself with near siblings like dialogs_delete, dialogs_reset_stage, or ai_delete, so sibling 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 description conveys the effect ('переписка остаётся; следующая сводка соберётся заново'), which implies when an agent would reach for it – to reset accumulated AI memory without losing the conversation. However, it never states when to use this rather than the alternatives, nor any preconditions.

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