research_deep

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

Annotations already indicate readOnlyHint and openWorldHint. The description adds context about multi-phase execution and evidence tier labeling, which are not covered by annotations. No behavioral contradictions.

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 plus a list, efficiently conveying purpose and process. It front-loads the main action and uses bullet points for phases and labels.

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?

With three parameters, an output schema, and annotations, the description provides sufficient context for an AI agent to understand the tool's purpose and output. It explains the multi-phase process and evidence labels, which are not detailed in the schema.

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 has 100% coverage, so baseline is 3. The description does not add meaningful details beyond the schema for parameters like topic, scope, or thinking_level. No explanation of enum options beyond what the schema provides.

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 runs multi-phase deep research with evidence-tier labeling, listing specific phases and claim labels. This distinguishes it from siblings like research_web or research_assess_evidence, which are single-purpose.

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 the tool is for in-depth research but does not explicitly state when to use it versus alternatives like research_web or research_assess_evidence. No guidance on when not to use or prerequisites.

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