research

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

No annotations are supplied, so the description carries the full burden of behavioral disclosure. It reveals that the tool queries 2-4 models in parallel, that synthesize:false shows side-by-side responses with latency and cost, and that search mode includes grounding. It does not mention potential rate limits or failure modes, but for a research tool the disclosed traits are substantial and non-contradictory.

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 front-loaded with the core purpose and then systematically covers usage guidance, modes, synthesize behavior, and query tips. While longer than the minimal two-sentence example, every sentence contributes meaningful information and the use of lists and colons keeps it scannable and well-structured.

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?

For a tool with 8 parameters, no annotations, and no output schema, the description is comprehensive: it explains modes, parameter defaults, behavioral differences (synthesize), query best practices, and cross-references the sibling search tool. It does not detail the exact response structure, but it states that synthesize:true produces 'one comprehensive answer' and synthesize:false shows responses 'side-by-side with latency and cost,' providing sufficient context for a research tool.

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%, providing a baseline of 3. The description adds value by explaining the semantic difference between modes (e.g., 'mode:search (default): web research with grounding' vs 'mode:ask: multi-model Q&A without web search') and the effect of synthesize (true: merge into one comprehensive answer; false: side-by-side with cost/latency), which enriches the schema's enum and boolean 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 opens with 'Multi-model parallel research. Queries 2-4 AI models simultaneously, then optionally synthesizes results,' which clearly states the tool's specific action and scope. It also explicitly distinguishes itself from the sibling 'search' tool by stating 'Use instead of search when...' making the purpose and differentiation unambiguous.

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 explicit guidance on when to use this tool over alternatives: 'Use instead of search when: (1) you need higher confidence via cross-validation across sources, (2) you want diverse perspectives on a topic.' It further breaks down mode-specific use cases (e.g., 'mode:ask: multi-model Q&A without web search — for architecture decisions, trade-off analysis'), giving clear context and alternatives.

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