Generate Research Ideas

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

With no annotations, the description bears full burden. It honestly states that ideas are derived from term overlap and gap templates, not a language model, and that scores are relative heuristics. It also clarifies that no experiments or code execution occur.

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 two sentences, covering purpose, method, and limitations with no wasted words. It is front-loaded with the core function.

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 absence of output schema and annotations, the description provides adequate context about input, method, and boundaries. It could be improved by briefly stating what the output contains (e.g., idea titles, scores) but is largely complete.

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 40% (only candidateMethods and focusGaps have descriptions). The tool description does not explain the meaning or usage of parameters like topic or selected_papers beyond what the schema fields imply. It adds minimal value over the 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 produces heuristic, keyword-based research-idea scaffolding from a topic and papers. It distinguishes itself from siblings like auto_literature_screen or discover_papers by focusing on idea generation, not screening or retrieval.

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 implies when to use (for generating ideas based on papers) and clarifies limitations (not from LLM, no experiments). However, it does not explicitly state when not to use or mention specific alternatives among siblings.

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