Снять разговор с шага

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

The description goes well beyond the annotations, adding rich behavioral context: the symptom the user sees (a silent bot), the side-effect of canceling deferred continuations with the rationale ('would fire into the void'), and the post-condition (next message restarts the scenario). This adds genuine value beyond the generic readOnlyHint/idempotentHint flags. No contradiction found — canceling scheduled continuations is inherent reset semantics, not destruction.

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, zero waste. The first sentence leads with the action and purpose, the second covers side effects and post-conditions. The vivid 'mute bot' and 'fire into the void' metaphors pack meaning into few words.

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 mutation tool with only two string parameters, no output schema, and no nested objects, the description is complete: it covers the trigger condition, the side effect, and the resulting behavior. Nothing essential is missing.

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 100% and both parameters (case, dialog) are already well-documented in the schema with their formats and defaults. The description adds nothing about parameters, which is acceptable per the baseline of 3 given full schema coverage, but there is no extra value either.

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?

The description uses a specific verb ('Освобождает' - frees/releases) and a specific resource (a conversation stuck at a wait node), clearly distinguishing it from sibling dialog tools like dialogs_list, dialogs_reply, or dialogs_delete. The real-world framing ('looks like a silently mute bot') makes the exact scenario unmistakable.

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 provides clear, specific context for when to use the tool: when a conversation is stuck at a wait node awaiting an answer that will never come. However, it does not name explicit alternatives or exclusions (e.g., 'use dialogs_delete if...'), so it falls just short of the top tier.

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