Поиск по приложению

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

Beyond the annotations, the description adds key behavior: 400 for any non-enum screen value, the default screen being afisha, the output semantics for afisha (eventId suitable for schedule tools), and the deep-link requirement for services. This is exactly the kind of behavioral context an agent needs and is entirely consistent with the read-only, idempotent annotations.

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 compact and every bullet earns its place: the strict-enum warning, the default screen, and per-screen behavior are all useful and non-redundant. The most important guidance ('СТРОГИЙ enum, угадывать бесполезно') is front-loaded, and formatting is easy for an LLM to parse.

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 is sufficient for the core call: it lists the screens, gives their meanings, warns about invalid values, and points to specialized grocery tools. Since an output schema exists, the return shape does not need full explanation in the description. Minor gaps remain (e.g., query syntax and pagination limits), but they are not blocking for invocation.

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?

With 0% schema description coverage, the description carries most of the parameter documentation. It enumerates all valid screen values, marks afisha as default, and clarifies what each screen returns. 'Полнотекстовый поиск' defines the query parameter in context, while limit is name enough to be understandable since its default is already in the schema.

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 opens with a specific verb and resource ('Полнотекстовый поиск по разделу приложения') and then details the distinct screen modes, so it is clear what tool does. It also distinguishes grocery from grocery_search/grocery_rank and ties afisha output to cinema_schedule/concert_schedule. However, it does not explicitly contrast itself with other search siblings like cinema_search or shop_search, so it falls just short of full sibling differentiation.

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 text explicitly says grocery should use grocery_search/grocery_rank instead and explains the requirements for those tools. It also warns that screen is a strict enum and that invalid values produce 400, which guides safe invocation. Still, it does not lay out exhaustive when-to-use-versus-alternatives rules for all other searching siblings, so it is clear but incomplete.

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