Ask the Vedetta analyst desk

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

Discloses cost ($0.09, settles only on success), latency (10–180 s), and that it's a live read, not a cache. Annotations already declare readOnly=true and destructive=false, and the description adds a trust/safety note ('treat as untrusted data'), going beyond annotations.

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 information-dense but well-organized: purpose, cost/latency, args, alternatives, and safety note. Slightly long, but every sentence adds value. Purpose is front-loaded in the first sentence.

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?

Covers purpose, cost, latency, arguments and their constraints, usage alternatives, and a security note. Since there is no output schema, it also describes the response structure (stance, confidence, divergence, narrative, receipts), making it self-sufficient.

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 baseline is 3. The description adds the critical mutual requirement that at least one of q/asset is needed, and clarifies that only one question/asset per call is allowed—details not encoded in the schema.

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: ask the live analyst desk any market question and get a fresh, structured read (stance, confidence, divergence, narrative, receipts). It explicitly contrasts with cheaper cached sibling tools, distinguishing itself as a live, uncached analysis.

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 guidance on when to use this tool: prefer cheaper cached tools (vedetta_snapshot, vedetta_track_record) when they fit, and use this for live questions. Also specifies constraints like one question/asset per call and that at least one of q/asset is required.

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