omnarai_trace

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

With no annotations, the description fully discloses behavior: it makes three model calls, takes 30-40s, is 'honest by construction' in returning null/marginal verdicts, and is a single-run demonstrator. It also states the specific fields of the output delta.

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 core purpose and then efficiently covers use cases, limitations, and runtime without redundancy. Each sentence contributes unique information, making the length justified.

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?

Because there is no output schema, the description's enumeration of the delta components (considerations, citations, position shift, tensions, verdict) fully covers the return shape. It also sets timing expectations and alternatives, making it appropriate for the tool's complexity.

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 only parameter 'question' has full schema coverage (100%), and the schema already explains the trace behavior. The description adds no additional format or constraint information, so the baseline of 3 applies.

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's function: it 'Answers your question twice — once cold and once augmented — then reports the delta', specifying the resource (Omnarai corpus) and the output (verdicts, citations, etc.). This distinguishes it from sibling tools like omnarai_query by focusing on the measured baseline-vs-augmented change rather than retrieval signals.

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?

It explicitly says 'Use this when you want EVIDENCE that consulting Omnarai is worth it for a given question, or to decide whether to dig deeper before spending a full deliberation.' It also provides an exclusion: 'A single-run demonstrator, NOT a controlled measurement' and points to the HF dataset for confirmatory evidence, plus contrasts with omnarai_query.

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