list_notifications

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds that the tool returns a list with date and text, and implies authentication ('текущего пользователя'). This enriches the behavioral context beyond annotations without contradiction.

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 extremely concise: two short paragraphs with three sentences total. Each sentence serves a clear purpose (purpose, usage, return), and the most critical info is front-loaded.

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?

Given the output schema exists, the description's mention of return fields (date, text) is sufficient. However, it doesn't clarify if the list is paginated or exactly how 'последних' (recent) is defined. Still, for a simple read-only tool with no parameters, it's mostly 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?

The input schema has no parameters, so schema coverage is 100%. Per guidelines, this yields a baseline of 4. No additional parameter description is needed, but the description confirms the tool requires no inputs.

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 verb 'Получить список' and resource 'уведомлений текущего пользователя Kwork'. It specifies the scope (current user) and the tool's purpose, effectively distinguishing it from siblings like get_dialog which handle individual conversations.

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 explicitly says 'Когда использовать: для просмотра последних уведомлений', providing a direct use case. It doesn't mention when not to use or alternatives, but no sibling directly replaces this tool, so the guidance is adequate.

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