Start a research job

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

Annotations indicate this is not read-only and is open-world. The description adds context about execution time differences but does not disclose the asynchronous nature, need for polling, or potential side effects. With annotations providing minimal safety info, more transparency is expected.

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?

Two efficient sentences: first states purpose, second details modes. No fluff, front-loaded.

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?

The description covers key dimensions (source, mode) for a job-starting tool. It omits return behavior or polling instructions, but sibling tools fill that gap. Adequate for its role.

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?

With only 25% schema coverage, the description meaningfully explains the 'mode' parameter (fast vs deep times) and implies 'from' options. However, 'query' and 'notebook' are not elaborated beyond 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 starts a research job on web or Drive, distinguishing it from sibling tools like research_poll and research_wait. The specific verb 'kick off' and resource listing are precise.

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 explicit guidance on when to use each mode (fast vs deep) with time estimates, but does not advise against using this tool versus alternatives or mention prerequisites.

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