digest_unread

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

The description explicitly discloses key behavioral traits: it does NOT mark messages as read ('Чтение НЕ помечает прочитанным'), is read-only, sorts by unread_count descending, returns newest-first, and includes a FloodWait limitation. Since no annotations are provided, the description fully carries the transparency burden and does so thoroughly.

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?

The description is moderately concise but contains fluff like 'KILLER-тул' and 'T9:', which add no functional value. It also repeats the 'not marked as read' point twice, making it slightly less tight. The core algorithm is clearly front-loaded, but the redundancy and informal jargon reduce efficiency.

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?

The description covers essential context: algorithm, sorting, read-only behavior, and rate-limit awareness. An output schema exists, so return values need not be described. It lacks edge cases (e.g., behavior when no unread chats exist), but overall it is sufficiently complete for a read-only digest 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?

The input schema already provides 100% coverage with clear descriptions for 'top' and 'per_chat', so the description does not add significant semantic value. It merely references these parameters in the algorithm without new details, aligning with the baseline for full schema coverage.

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 clearly states the tool's purpose as a digest of unread messages ('дайджест непрочитанного') and outlines the algorithm (iter_dialogs → top chats with unread_count > 0 → fetch recent messages). It distinguishes itself from sibling tools like get_history or list_chats by focusing on unread counts and read-only aggregation.

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 implies the tool is for catching up on unread messages and mentions read-only behavior, but it does not explicitly state when to use it over alternatives or provide exclusions. No named sibling alternatives are given, so usage context is only implied.

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