run_research_task

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

With no annotations, the description bears the full burden. It correctly indicates the tool is asynchronous by stating it returns a task_id for polling. However, it does not disclose whether the task can be canceled, what happens if it fails, or any rate limits. The behavior is partially transparent but lacks depth.

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, containing three sentences plus an example. It avoids unnecessary fluff and front-loads the key purpose and async nature. However, the information about polling and webhooks could be more structured (e.g., bullet points) for clarity.

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 the main aspects: purpose, async polling, and optional parameters. However, it does not explain how to retrieve the result (implicitly through the sibling tool 'get_research_task_result'), nor does it mention any limits on query length or concurrency. Given no output schema, more detail on the return value beyond a task_id would improve completeness.

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 input schema has 100% coverage with descriptions, but the tool description adds significant value by providing natural language examples for the query parameter, explaining contextual usage for timezone and location, and detailing the output_fields with a cross-reference to documentation for complex schemas. This goes beyond the schema's basic 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 it executes a one-time deep web research task that searches, reads, and synthesizes information. It provides an example ('latest AI startup funding announcements') and mentions returning a task_id for polling. However, it does not explicitly differentiate from the sibling tool 'run_browsing_task', which might be used for simpler tasks.

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 does not provide any guidance on when to use this tool versus its siblings (e.g., run_browsing_task) or when not to use it. There are no prerequisites or exclusions mentioned, leaving the agent to infer usage context from the description alone.

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