deep_research

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

With no annotations, the description carries the full burden. It does disclose several behavioral traits: aggregates results, ranks by reliability, removes duplicates, and produces a detailed report. However, it omits potential side effects, dependencies, or limitations (e.g., no mention of network calls, rate limits, or that it is purely read-only).

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 primary purpose and then details the output components. While the list of report elements is long, each item adds meaningful context. No wasted words, but it could be slightly more concise by trimming the exhaustive list.

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 no output schema, the description does a good job explaining the return value (a technical report with specific sections). It also covers the scope (across ALL sources) and the research process. It doesn't address how depth modifies behavior, but the schema's enum description partially covers that.

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?

The schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds some semantic reinforcement (e.g., 'version considerations' aligns with versions parameter), but it doesn't provide syntax, format, or usage details beyond what the schema already includes.

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 uses a specific verb ('Orchestrate') and clearly defines the resource ('comprehensive research across ALL sources for a Protheus topic'). It distinguishes from siblings by emphasizing aggregation and report generation, unlike the targeted search tools like search_protheus_docs or search_community.

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 clearly implies this is the go-to tool for comprehensive research across all sources, while siblings handle specific searches. It does not explicitly state exclusions but the 'ALL sources' phrase provides clear context for when to use it over more focused alternatives.

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