Дочекатись запуску

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

With no annotations, the description carries the full burden, and it discloses key behavioral traits: it blocks until completion, emits progress notifications while waiting, and does not abort the run on timeout. It does not go into return-shape details, but the behavior most relevant to an agent is clearly stated.

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, all load-bearing: what it does, what progress signals it sends, and what happens on timeout. The most important fact is front-loaded and nothing is redundant.

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 simple blocking-wait tool, the description covers the workflow, timeout semantics, and relation to glm_status. Without an output schema or annotations, a bit more detail about the returned result/state shape would make it fully complete, but not much is missing for correct 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?

Schema coverage is 50%: timeout_sec already has a description with a default, and run_id is self-explanatory from the run-management sibling set, but the description itself adds no parameter-level detail. This is acceptable but not additive.

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 ('Чекає завершення фонового запуску') and states the output ('віддає результат'). It differentiates the tool from glm_status by explicitly rejecting blind polling, so an agent can select it correctly among the run-management siblings.

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?

It names the alternative glm_status and tells the orchestrator to use this tool to get progress rather than poll status blindly. It also sets expectations for timeout behavior ('на таймауті запуск НЕ обривається'), which is important usage guidance.

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