debate_auto

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

The annotations already indicate destructiveHint=true, readOnlyHint=false, idempotentHint=false. The description adds useful behavioral context beyond this: it explains the internal process (generates positions and independent challenges, runs the protocol, returns the convergence result) and states the prerequisite of non-empty context_documents and an API endpoint. It does not contradict the annotations, though it doesn't elaborate on the destructive side effects.

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 compact and front-loaded: a deprecation warning, a one-sentence function summary, then required conditions and behavior. No filler or repetition of the schema.

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?

The description conveys the tool's high-level behavior, prerequisites, and return value ('returns the convergence result') in a concise way. However, with 17 parameters, no output schema, and minimal parameter semantics, an agent invoking this tool would be under-informed about many configurable options. The deprecation reduces the need for exhaustive detail, but there are still notable gaps.

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?

There are 17 parameters and the schema has 0% description coverage. The description only mentions 'context_documents' as needing to be non-empty and implicitly references 'prompt' in the preferred debate call, but provides no explanation of deep_n, effort, fresh_n, pause_at, delivery_mode, injection_mode, or the other parameters. This is far below what a 17-parameter tool needs.

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 states 'Run a complete debate automatically in a single command', clearly identifying the verb, resource, and scope. It distinguishes itself from siblings by declaring DEPRECATED and pointing to 'debate(prompt, mode=...)' as the preferred alternative, while also listing generated positions, challenges, and the convergence result.

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 'prefer debate(prompt, mode=...)' and gives a deprecation warning, which is an explicit alternative. It also states the preconditions 'Requires non-empty context_documents and a configured API endpoint', giving clear context for when this tool can be used.

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