harness_research

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

With no annotations, the description fully discloses that the tool returns immediately (non-blocking), runs in background, and uses affordable models ($0.01/run). It also mentions PDF availability limitation (macOS only). All behavioral traits are transparently communicated.

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 well-structured with a clear heading, an IMPORTANT note, and a numbered workflow. Each sentence is purposeful, no redundant text, efficiently conveying essential information in a few paragraphs.

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's complexity (async, 5 parameters, multiple outputs), the description covers all key aspects: async behavior, polling, output format limitations, and cost. No output schema exists, but the description explains that harness_status returns file paths, completing the context.

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%, so parameters are well-described structurally. The description adds value by explaining defaults (e.g., provider='kimi', model='kimi-k2.5', formats=['html','docx']) and the purpose of the tool, though the schema itself already covers basic parameter semantics.

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 explicitly states it 'start[s] a deep research session' with multi-source search and report generation. It lists sources (Tavily/Brave/arXiv/PubMed/Tushare) and output formats (HTML/DOCX/PDF), clearly distinguishing it from siblings like harness_search (likely simple search) and harness_status (status polling).

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 provides explicit step-by-step workflow: call this tool, get task_id, poll harness_status every 30-60s until completion. It warns against idle waiting and notes the ~8-12 minute runtime, giving clear when-to-use and how-to-use guidance.

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