research_start

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

With no annotations, the description must disclose behavioral traits. It mentions async behavior via polling and provides mode durations (fast ~30s, deep ~5min). However, it does not explicitly disclose that it may create a new notebook if notebook_id is omitted, nor does it discuss error cases or authentication requirements.

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 concise: a two-sentence summary followed by bullet-like usage examples and a clear workflow. Every sentence adds information without redundancy, and key details are 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?

Given the tool's async nature, multiple modes, and optional notebook creation, the description covers the core purpose, usage, workflow, and mode trade-offs. It lacks details on return values (though output schema exists) and potential errors, but is sufficient for typical agent guidance.

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 baseline is 3. The description adds value by explaining mode characteristics (time, source count) and source options (web/drive), but does not significantly extend beyond what the schema comments already provide.

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 / fast research' to 'search web or Google Drive to FIND NEW sources.' It provides specific use case examples and differentiates from sibling research_status and research_import by outlining the workflow sequence.

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 gives explicit guidance on when to use this tool via examples like 'deep research on X' and 'search web for Z'. It also prescribes a multi-step workflow: research_start → poll research_status → research_import, helping the agent understand the proper invocation sequence.

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