Поиск сервисов в каталоге ЕЛК

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

Annotations already declare read-only, idempotent, open-world behavior, so the description focuses on what it adds: the exact result fields (id, name, description, direct link, relevance score) and the subtle fact that `categories` counts come from ALL search categories even though results are services-only. That is genuinely non-obvious behavior an agent would otherwise misread.

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, front-loaded with the verb, resource and endpoint, then the return shape. Slightly dense with parenthetical metadata (catalog size, date) that is helpful but close to excess; still every clause carries information.

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?

With no output schema, the description carries the return-value burden and does so well, naming each field and explaining the categories counter semantics. What is missing is only a note on result ordering/limit behavior and explicit sibling routing, which are secondary for a simple two-parameter search.

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%, with `query` already documented with examples and `limit` bounded 1-50 by the schema. The description adds only topical framing of what queries hit (services catalog), and never mentions the limit parameter, so it does not exceed the schema baseline.

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?

States a specific verb and resource ('Полнотекстовый поиск по каталогу сервисов ЕЛК'), names the backing endpoint and category, and enumerates what is findable (справки, заявки, психолог, антиплагиат). An agent can tell immediately this is a service-catalog text search, distinct from elk_get_user_info or elk_list_requests.

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?

Usage is only implied: the note that `categories` counters reveal whether it is worth also searching people/departments hints at follow-up routing. There is no explicit statement of when to prefer this over siblings like elk_get_section or elk_list_requests, and no exclusions.

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