Multi-turn chat

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

The annotation set (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) already tells the agent this is a non-destructive but stateful open-world call. The description earns credit beyond that by disclosing the critical operational fact that the server keeps no state, so the entire history must be resent each turn. It does not mention cost, rate limits, or truncation behavior for long histories.

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?

Three short sentences, each doing distinct work: what it does, the statefulness contract, and the routing alternative. The default model is front-loaded at the end where a caller will look for it, and there is no filler.

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?

With six parameters, full schema coverage, and annotations, the description covers the essentials: statelessness, the history contract, and the sibling comparison. The lighter note is return shape — there is no output schema, so a brief mention of what the reply contains (assistant text plus optional reasoning text) would close the remaining gap.

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 every parameter is already documented in the schema, including the default model, token cap, and reasoning-effort enum. The description reinforces that `messages` carries the whole history (explaining why via statelessness) and repeats the default model, but adds little beyond the schema text. Baseline 3 is appropriate.

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 (continue a multi-turn conversation with an Obscurify.ai model), specifies exactly what the caller must supply (the whole history in `messages`), and names the sibling it is not (`ask`). An agent can distinguish it from `ask` and `second_opinion` without opening either schema.

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?

Explicitly routes single-question use to the sibling `ask`, which is the key decision point for this tool family. It does not address the other siblings (`second_opinion`, `generate_image`, `list_models`) or state any when-not-to-use condition beyond that one comparison.

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