deep_research

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

With no annotations, the description carries the full transparency burden. It discloses key behavioral traits: the 5-15 minute duration and the significant side effect that it 'blocks other ChatGPT operations during research.' It also mentions the return type (comprehensive results with sources). While it doesn't cover potential errors or cancellation, the most critical behaviors are surfaced.

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 two sentences: the first states the purpose and scope, the second adds a critical warning and expected output. Every sentence provides necessary information, with no fluff or repetition. It is front-loaded with the primary action and concise enough to be parsed quickly.

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 tool with no output schema, the description adequately covers what the agent can expect (comprehensive results with sources) and the major operational constraint (blocks other operations). It could go further by specifying whether the blocking is global or per-resource, or how the timeout parameter should be interpreted relative to the 5-15 minute estimate, but these are minor gaps. Overall, the description is complete enough for correct selection and invocation.

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 both query and timeout_minutes are documented in the input schema. The description adds no additional meaning about these parameters; it doesn't explain how the timeout interacts with the stated 5-15 minute research time. The description does not need to compensate since the schema is complete, so a baseline score of 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 action ('Run ChatGPT Deep Research') and the resource ('on a query'), then elaborates with 'Performs in-depth web research' and 'Returns comprehensive results with sources.' This specific verb+resource combination distinguishes it from sibling tools like council_discuss or ask_model, which are discussion/query tools rather than research tools.

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 clear context for when to use the tool: for in-depth web research via ChatGPT's Deep Research mode. It implies it is best for comprehensive queries rather than quick questions, but it does not explicitly name alternatives or state when not to use it. The lack of explicit exclusions prevents a 5, but the context is unambiguous.

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