research_start

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it's a search operation that initiates research, specifies time and result estimates for modes (fast: ~30s, ~10 sources; deep: ~5min, ~40 sources), notes that deep mode is web-only, and explains notebook creation behavior ('creates new if not provided'). However, it doesn't mention error conditions, rate limits, or authentication needs, leaving some gaps.

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 well-structured and front-loaded, starting with the core purpose, followed by usage guidelines, workflow context, and parameter details. Every sentence adds value without redundancy, and it efficiently covers essential information in a compact format, making it easy for an AI agent to parse and understand.

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 (initiates research with multiple parameters), no annotations, and an output schema (which handles return values), the description is complete enough. It covers purpose, usage, workflow, and all parameter semantics, providing a comprehensive understanding without needing to explain output details, which are handled by the output schema.

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 description adds significant meaning beyond the input schema, which has 0% description coverage. It explains all 5 parameters: 'query' with an example ('quantum computing advances'), 'source' with allowed values (web|drive), 'mode' with details on fast vs deep, 'notebook_id' behavior ('Existing notebook (creates new if not provided)'), and 'title' purpose ('Title for new notebook'). This fully compensates for the schema's lack of descriptions.

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 purpose with specific verbs ('search web or Google Drive to FIND NEW sources') and distinguishes it from siblings by explicitly naming the research workflow (research_start → poll research_status → research_import). It provides concrete examples of use cases ('deep research on X', 'find sources about Y'), making the purpose unambiguous and differentiated.

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 explicitly states when to use this tool ('Use this for: "deep research on X", "find sources about Y", "search web for Z", "search Drive"') and provides a workflow context ('Workflow: research_start -> poll research_status -> research_import'), which helps differentiate it from sibling tools like notebook_query or source_list_drive. It also clarifies mode restrictions ('deep (~5min, ~40 sources, web only)'), offering clear usage guidance.

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