research_start

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

With no annotations, the description carries the full behavioral burden and does so thoroughly: background process with done marker, sqlite progress, partial status, report synthesis pipeline, cron health check, auto-archive, and llm_planner mode. It even warns about double-launch race conditions.

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?

The description is dense and front-loaded, with structured WHEN/NOT WHEN sections. It is longer than typical but each sentence adds a distinct operational fact; a few cryptic phrases like 'corner waves' could be clearer.

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 7-parameter tool with no annotations and an output schema, the description covers the full lifecycle: when to launch, how background runs, how completion is signaled, downstream synthesis, failure/partial semantics, and dead-cron warning. Nothing essential for correct invocation 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 description coverage is 0%, so the description must add semantics. It explains feeds as a search-engine-free first leg, queries as optional, background as a separate process with marker, and llm_planner as an LLM layer. However, domains_limit and target_sources are only vaguely tied to 'N sites' and 'unique domains'; topic is left to inference.

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 clearly frames the tool as a research campaign targeting N distinct sites with a progress counter, and explicitly distinguishes it from synchronous research and research_resume. The scope and intent are immediately recognizable.

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 contains explicit КОГДА/НЕ КОГДА (when/when-not) guidance, directing agents to research for synchronous needs and research_resume if a campaign is already running. It also explains when feeds should be used and when queries can be omitted.

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