Сбросить кэш данных ВШЭ

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

Annotations already declare idempotent, non-destructive, not-open-world, so safety is covered; the description adds genuinely new behavior facts: a 2–30 minute TTL, which resources are cached and why, and that the call must be followed by re-issuing the query. It does not say whether the reset itself can fail or whether existing cache entries for other services are unaffected in edge cases, so a small gap remains.

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?

Three sentences: rationale, action, parameter. Front-loaded with why the cache exists before the instruction. The first sentence is long but every clause (TTL, cached resources, browser-avoidance rationale) contributes useful context.

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?

A one-optional-param mutation with no output schema; the description covers the affected tools, cache lifetime, the trigger scenario, the required follow-up action, and the scope parameter. Nothing needed to call it correctly is missing.

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% and the enum values are already documented, so the baseline is 3. The description adds the semantic purpose of the parameter ('сужает сброс до одного сервиса'), which helps the agent decide to use it rather than the default, nudging it above 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: reset the in-memory cache of results from lms_*/elk_* tools and the my_today/my_week/my_deadlines summaries. Naming the affected siblings explicitly distinguishes it from hse_changes_reset and the data-reading tools.

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?

Gives the exact condition to invoke it ('если нужно гарантированно свежее значение'), a concrete trigger example (right after submitting a work or request), and the follow-up step (repeat the request). It also explains what scope does, so the agent knows when to narrow the reset.

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