search_with_synthesis

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context: explains the waterfall multi-engine verification, states that no external LLM call is required but outbound network requests are made, and mentions the return of a prompt_hint. No 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 concise, front-loaded with the core purpose, and every sentence adds value. Usage guidelines and annotations are clearly separated, and there is no unnecessary verbosity.

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 has 5 parameters and no output schema, the description adequately covers its behavior, return format (structured results + prompt_hint), and network requirements. It differentiates well from sibling tools. Minor gap: does not detail the structure of results, but acceptable for a search 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 80% (4 out of 5 parameters have descriptions). The description does not add parameter-specific information beyond the schema, so it meets the baseline of 3. No additional semantic value is provided.

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 performs deep search with waterfall multi-engine verification and returns structured results plus a prompt_hint for synthesis. It explicitly differentiates from siblings by mentioning 'complex queries needing multi-source verification' and contrasts with 'free_search' for simple queries.

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 'Best for' and 'Not recommended for' sections, naming the alternative tool 'free_search' and giving clear context on when to use this tool (complex queries) versus when not to (simple fact-finding). Also notes that no external LLM call or API key is needed.

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