deep_research

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

No annotations are provided, so the description carries the full burden. It explains that the tool aggregates results, scores by relevance, and removes duplicates. It does not mention any destructive actions or side effects, but as a read-only research tool, this is sufficient. The output schema further clarifies return values.

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 well-structured with clear sections (main purpose, available backends, usage guidance). It is informative without being overly verbose. Some redundancy exists (backends listed twice), but overall efficient.

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?

Given the complexity of 5 parameters, 1 required, and the presence of an output schema and sibling tools, the description is thorough. It covers what the tool does, how to use it, backend selection guidance, and references to alternative tools. No gaps in essential information.

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 baseline is 3. The description adds value by explaining the purpose of search_terms (multiple related queries), listing available backends, and providing usage recommendations for backends. This goes beyond the schema's descriptions.

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 states that the tool performs deep research across multiple search terms using specified backends, aggregates results, scores by relevance, and returns the most relevant content with duplicates removed. It distinguishes itself from sibling tools like deep_research_google and deep_research_ddgs by mentioning them as shortcuts.

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?

The description includes a dedicated 'USAGE GUIDANCE FOR LLM' section detailing when to use different backends, how to ask users for preferences, and specific recommendations for various use cases. It also mentions sibling tools as alternatives for single-backend scenarios.

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