deep_research

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

With no annotations, the description carries the burden of disclosing behavior. It reveals key traits: async execution, polling requirement, expected duration (5-20 minutes), and cost ($2-5). This covers the most critical operational behaviors, though it does not mention failure modes or auth specifics.

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 sentences, front-loaded with the action and immediate next step. No wasted words. Every clause adds value: async nature, return type, polling interval, time and cost expectations.

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 (async, expensive, slow) and lack of output schema, the description is complete. It tells the caller what to expect (interaction_id), how to proceed (poll research_get), and sets expectations (time, cost). This is sufficient for correct invocation and orchestration.

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 description coverage is 100%, so the baseline is 3. The description adds no parameter-level details beyond what the schema already provides (e.g., defaults, enums, overrides). It does not enhance understanding of the parameters, but also does not need to.

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 states a specific verb ('Fire'), a clear resource ('Gemini Deep Research task'), and the asynchronous nature. It distinguishes from siblings by explicitly naming research_get as the polling endpoint, making its role and relationship to the research workflow clear.

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?

Provides clear operational guidance: returns an interaction_id and instructs to poll every 60s. This implies when to use it (start research) and how to follow up, but does not explicitly compare against alternatives like generate or research_followup. No exclusions are needed given the distinct purpose.

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