submit_research_job

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

With no annotations, the description discloses the deferred nature, background processing with xAI's tools, and the return dict structure. It does not mention error handling or rate limits, but covers key behavioral traits beyond the schema.

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 with a clear intro sentence, bullet-list args, and return section. No unnecessary words; every sentence adds value.

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 (3 params, 1 required, output schema present), the description covers the workflow, parameter constraints, and return value. No critical gaps.

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?

Despite 0% schema coverage, the description explains each parameter's purpose and constraints: prompt as the research question, model as optional Grok model id (default planning model), agent_count as multi-agent fan-out only accepting 4 or 16. Adds significant meaning over bare 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 it submits a long-running research task as a deferred job and returns immediately, using verbs like 'submit' and 'run in the background'. It distinguishes from siblings like get_research_job (polling) and list_research_jobs (listing).

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 says to poll get_research_job for results, implying this is for long-running tasks. It provides context on parameters (model optional, agent_count only 4 or 16) but does not explicitly exclude synchronous alternatives like 'agent' or 'chat'.

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