research

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

With no annotations, the description fully discloses behavior: decomposes into sub-queries, parallel search, fetching, synthesis, and returns detailed structures (report, brief with key_findings/highlights/sections, gaps). It also explains optional LLM dependency and parameter effects on timing and output.

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 long but well-structured, with a clear summary first, then LLM-optional nuance, then parameter details, then return shape. Every sentence adds value, though it could be slightly more terse without losing clarity.

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 complex tool with 10 parameters, no output schema, and nested objects, the description is remarkably complete. It covers return fields (citations, sources, brief with topics/highlights/gaps), phases, and optional LLM behavior. Missing only error/exception details and explicit prerequisites (API key mentioned as optional).

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 coverage is 100%, but the description adds significant meaning: explains depth time estimates, max_sources usage, citation formats, include_full_markdown effects, and schema parameter for structuring output. This goes beyond the schema's basic 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 clearly states the tool is for multi-step research on complex questions, decomposing into sub-queries, searching, and synthesizing a cited report. It distinguishes itself from manual chaining of 'search' and 'fetch' by offering multi-source synthesis.

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 explains when to use this tool (complex questions requiring multi-source synthesis) and how it compares to alternatives (beats chaining search+fetch manually). It also provides guidance on handling outputs when no synthesis LLM is configured. However, it does not explicitly state when not to use it.

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