Поиск анекдотов

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

With no annotations, the description carries the full burden and does well: it discloses read-only/no-side-effects, relevance ordering via ts_rank, stemming behavior, and the empty-result consequence of a missing query. What it omits is the shape of returned records, but that is a modest gap for a read tool.

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-loads what the tool is and the stemming example, then constraints, then pagination. Mostly efficient, though the limit default/ceiling restatement duplicates the schema and could be trimmed.

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 three-parameter read-only search with no output schema, the description covers ranking, language/morphology, required query, and pagination. Only the returned record shape is unaddressed, which is a minor omission.

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%, so limit/offset defaults and bounds are already documented and the description largely repeats them. The one genuine addition is the morphology explanation showing that 'врач' matches 'врачи'/'врачом', which clarifies query semantics beyond 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?

States a specific verb+resource: full-text keyword search over joke records, with Russian-language scope and ranking. It is clear what the tool does, but it never names how it differs from siblings such as get_jokes_by_category or random_joke, leaving that inference to the agent.

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: 'query обязателен; поиск без него вернёт пустой результат' tells the agent the parameter is mandatory but not when to prefer search over category browsing or random retrieval. No explicit when-to-use or when-not-to-use guidance appears.

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