Сводка на сегодня

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

Annotations already cover read-only, idempotent, open-world, non-destructive, so the description's added value is the graceful-degradation contract: if a source is unreachable the summary is still returned and per-source status lives in `sources` (ok/error/skipped, error text, warnings). That is a real behavioral trait beyond the annotations; it stops short of stating cost, rate limits, or freshness/caching of the aggregated data.

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?

Front-loaded with the 'today' scope, then contents, then return shape and the failure caveat. The item field list (kind, when, title, course, place, overdue, unread, source, ...) and the sources description partly duplicate the output schema, which is the only slack in an otherwise dense paragraph.

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 zero-argument aggregator spanning two external systems, the description covers contents, ordering guarantees, return envelope, and partial-failure handling. With an output schema present, no further return-value detail is required; nothing an agent needs to invoke it correctly is absent.

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?

Zero parameters, so the baseline is 4; no parameter semantics are needed or missing. The description correctly spends no space on 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?

Enumerates exactly what the tool aggregates for 'today': classes, deadlines (with a precise window — all overdue unsubmitted plus through end of tomorrow) from SmartLMS and ЕЛК, exams, unread mail/notifications, active requests and tasks. Scope is unambiguous and separable from my_week / my_deadlines by its 'today' window, though no sibling is named explicitly.

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 framing 'Что у студента сегодня' plus the exact deadline window gives clear context for when this tool applies (daily briefing requests) rather than alternatives like my_week. It never states exclusions or explicitly routes to the sibling tools, so guidance remains inferential rather than directive.

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