deep_research

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

The description discloses that the tool performs multiple operations (search, parallel scrape, synthesize), which is helpful. However, it does not mention potential side effects like saving to memory (implied by the saveMemory parameter) or behavioral traits such as longer execution time or cost implications. Without annotations, the description carries the burden for transparency, and it only partially meets it.

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 extremely concise at 13 words. While brevity is valued, this description is underspecified and missing critical information. It is not front-loaded effectively because it does not immediately clarify what the tool does in a self-contained way (e.g., 'research' is vague without context). It earns a 3 because it is not verbose but is too short to be fully useful.

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 tool's complexity (orchestrated multi-step process, 4 parameters, no output schema), the description is severely incomplete. It does not explain what 'synthesize' means (e.g., returns a summary, a report, or structured data), the significance of saveMemory, the behavior of depth levels, or how maxSources interacts with scraped pages. A complete description would require at least a few sentences to cover these aspects.

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?

The input schema has four parameters with no descriptions (schema description coverage 0%). The description does not explain any of the parameters (topic, depth, maxSources, saveMemory) beyond what is obvious from their names. For example, it does not clarify what each depth level ('quick', 'standard', 'deep') entails or how maxSources affects the search and scrape process. The description adds no semantic value to the schema.

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 the tool performs 'deep research' through orchestrated search, parallel scraping, and synthesis. This distinguishes it from sibling tools like search_web (search only) and scrape_page (scrape only), as it combines multiple steps into one call.

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 provides no explicit guidance on when to use this tool versus alternatives. For example, it doesn't specify when deep_research is preferred over manually chaining search_web and scrape_page, or when not to use it (e.g., if only a single source is needed). The implied usage is for comprehensive research, but no exclusions or alternatives are mentioned.

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