run_discussion

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

No annotations exist, so the description carries the full burden. It usefully discloses that the run is 'bounded' and that the token limit spans the entire discussion rather than a single agent's output, but says nothing about cost, latency, whether the run is idempotent, or what control the caller retains mid-run.

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?

Roughly 50 words, front-loaded with the core action, then the ordering constraints. The hard line breaks make it slightly choppier than needed, but no sentence is wasted.

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?

Run a bounded multi-agent discussion with an independent judge. Provide at least two participant names; `judge` can be omitted if a profile with role `judge` exists. The token limit applies to generated completion tokens across the whole discussion. Missing: what `max_rounds` controls and when to prefer this over run_solo.

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 description coverage is 0% across 5 parameters, so the description must compensate. It clarifies the `agents` minimum (two), the `judge` omission fallback, and the scope of `max_output_tokens`, but leaves `task` and `max_rounds` entirely unexplained — 2 of 5 parameters remain pure guesswork.

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 a bounded multi-agent discussion with an independent judge'), which is clearly distinguishable from the agent-CRUD siblings. It stops short of naming run_solo as the contrasting one-on-one alternative, so the multi-agent framing does the separation implicitly.

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?

Gives concrete preconditions in 'Provide at least two participant names' and the judge-omission rule, which is real conditional guidance. However it never says when to pick this tool over run_solo, nor what kinds of tasks warrant a multi-agent debate versus a single run.

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