deep_research

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

The description adds substantial context beyond the annotations: it discloses the multi-step process (planning subquestions, searching multiple sources, extracting claims, cross-verifying), the output format (citation-backed), the time cost, and a prerequisite (allow_deep_research in config). This is exactly the kind of behavioral detail that helps an agent understand the trade-offs.

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 dense sentences, each earning its place: first explains what it does, second gives usage guidance, third states time and permission requirements. No fluff, front-loaded with the primary purpose.

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 complex research tool with no output schema, the description covers the process, duration, return value (citation-backed answer), and prerequisites. It fully compensates for the lack of an output schema and gives the agent enough context to invoke it correctly.

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 already provides 100% description coverage for all three parameters, including defaults and ranges. The description does not add parameter-level semantics beyond what the schema provides, but it also doesn't need to. Baseline 3 is appropriate.

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's verb ('conduct deep, multi-step web research'), the resource (web/topic), and the output (citation-backed answer). It distinguishes itself from siblings like web_search and web_fetch by emphasizing multi-step planning, cross-verification, and synthesis.

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 explicitly says when to use it: 'for questions needing current information, evidence verification, or multiple perspectives.' It also gives a time expectation (1-3 minutes) which helps the agent decide if this heavy tool is appropriate. It does not explicitly name alternatives or exclusion criteria, but the contrast with simpler search tools is implied.

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