Chat with an LLM

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

With annotations already declaring openWorldHint=true and non-idempotent/non-destructive, the description adds genuinely useful behavior: per-token credit billing at a 50% markup on provider price, non-streaming execution, and statelessness requiring the entire conversation each call. It omits failure modes, rate limits, and what happens on insufficient credits, so it is helpful but not complete.

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?

It is front-loaded with the operation and pricing, and nearly every clause carries information an agent needs. The heavy nested parentheticals (provider list, billing formula, model-listing hint, image shape) make it dense to scan, which is the only real cost.

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?

There is no output schema, and the description covers the return payload anyway (reply text, token usage, credits charged). Combined with pricing, statelessness, model discovery, and multimodal input format, an agent has enough to call it correctly on the first try.

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?

At 50% schema coverage, the description compensates for the undocumented 'messages' parameter by explaining the stateless full-history requirement and restating the image-part shape qualified by 'on vision models'. It says nothing about maxTokens (default 2000, cap 16000) or reasoningEffort behavior beyond the schema's own notes, leaving one gap.

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?

States a specific verb and resource ('Run one chat completion on VIVID's LLM routing') and enumerates the providers behind it, which cleanly separates it from the image/video/music generation siblings. 'Non-streaming' further pins down the exact operation.

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 gives usable context: list models via vivid_list_models type="llm", expect credit billing at provider price + 50%, and pass the full conversation each call. It never explicitly says when to prefer this over a sibling or what it cannot do, so it stops short of full when/when-not guidance.

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