research

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

With no annotations, the description carries the full transparency burden and does well: it discloses URL deduplication, snippet returns, parallel article fetching with auto resource allocation and max_parallel limits, and 24-hour caching. It also notes the gpt-researcher quick_search pattern, adding useful behavioral context beyond the schema.

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 compact and front-loaded with the core purpose ('Deep-поиск ОДНИМ вызовом'), followed by parameter explanations and a concrete example. Every sentence adds value, and the structure is easy to scan despite being information-dense.

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 6-parameter tool with no annotations, the description covers the main workflow, caching, deduplication, parallel fetching, and return shape (snippet list). However, it misses semantics for two parameters (max_chars, article_only) and does not mention error cases or edge behavior; the presence of an output schema reduces the need to describe return values.

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 compensate. It explains queries (multiple formulations, agent plans subqueries), fetch_top (read top-N sources), and max_parallel (explicit limit), but leaves max_chars and article_only semantically unexplained, and max_results_per_query appears only in the example without clarification.

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 states the tool performs deep web search in a single call, taking multiple query formulations, deduplicating URLs, returning snippets, and optionally fetching top-N source texts. This clearly distinguishes it from siblings like web_search or fetch_page by emphasizing multi-query planning, deduplication, and integrated fetching.

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 frames this as 'deep search in one call' and says the agent itself plans subqueries, making it clear when to use it for multi-angle research instead of repeated single searches. It provides a concrete example, but does not explicitly state exclusions or name alternative tools for cases where this tool is not appropriate.

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