rx_help_search

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

Annotations cover the safety profile (readOnlyHint, openWorldHint=false, idempotentHint=false), so the bar is lower, yet the description adds real behavioral context: help is stored locally and downloaded on first call, requiring the query to be repeated after a few minutes. That first-call non-idempotent side effect aligns with idempotentHint=false and is exactly the kind of latency/state caveat agents need. It stops short of describing ranking or result-count behavior, so not a 5.

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 core purpose and scope, then usage, return shape, alternative routing, and the download caveat. Every sentence carries information; the only mild cost is that the caveat about local storage and re-querying could be tightened, keeping it just under maximum.

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?

No output schema, yet the description explains the return (articles with a fragment and file name) and points to rx_help_topic for full text. Combined with scope, alternatives, and the first-call download behavior, an agent has everything needed to call this correctly.

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 the schema already documents all three parameters and the baseline is 3. The description goes beyond it by explaining query matching semantics — word search accounting for morphology, and reformulation advice when hits are sparse — which materially shapes how an agent phrases the query parameter.

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 (поиск по справке Directum RX), scopes it to the same version as the user's stand, and explicitly names what it is NOT for versus siblings rx_help_topic and rx_kb_search. An agent can distinguish it from every neighboring KB/help tool without opening a schema.

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 explicit when-to-use (вопросы о самой системе: устройство механизма, настройка, значение поля/статуса), when-not-to-use (правила и инструкции компании — в rx_kb_search), and the alternative for reading full text (rx_help_topic). Also provides an in-tool fallback: reformulate the query if results are few.

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