generate_experiment

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

With no annotations, the description fully discloses the async behavior, pipeline steps, expected runtime, immediate return of a job handle, and the need to poll. It also describes error cases, input validation, and dependencies like ANTHROPIC_API_KEY, and includes a research-only disclaimer.

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 with purpose and async behavior. It is fairly long but each section (overview, async explanation, args, returns) earns its place. Minor redundancy could be trimmed, but overall it is appropriately concise for the complexity.

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 complexity of an async multi-step pipeline, the description is highly complete. It explains the pipeline steps, the final TransBrief content, error handling, and return shapes for both statuses. The output schema is mentioned, and the description covers everything needed for correct usage.

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 description coverage, the description provides detailed parameter documentation in an Args section: observation with length constraints and examples, focus_drug with default and optional usage. This adds significant meaning beyond the 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 the tool generates a 'grounded translational research brief' from any clinical/biomedical observation, with specific examples. It differentiates itself from siblings by explaining its async nature and that it initiates a pipeline, while 'get_experiment_result' is for polling and 'search_grounded_evidence' is for searching.

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 provides explicit when-to-use guidance: for any clinical/biomedical observation. It explains the async workflow and the need to poll for results. It gives example inputs but does not explicitly state when not to use it, though the context makes it clear.

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