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

Annotations already set readOnlyHint=false and destructiveHint=false, so the description adds vital context: it spends credits, starts a background job, and returns a session ID for an async result. This goes well beyond annotations by explaining the non-read-only, non-idempotent nature of credit consumption and async processing. No contradictions with 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 two concise sentences, front-loading the core purpose and then adding key behavioral notes. Every sentence provides essential information—what the tool does, async nature, credit cost, and parameter guidance. No wasted words.

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?

Given the existing output schema and 100% parameter coverage, the description covers the key points: purpose, async return, credit cost, ownership requirement, and optional persona. It could mention the expected runtime or how to retrieve results (e.g., using session ID) for full completeness, but it is adequate for an agent to use the tool correctly.

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 meaning by explaining that personaType is optional (defaults auto-selected) and ties language to response language. It doesn't elaborate on ideaId beyond stating ownership requirement, but the schema already describes it as 'the idea ID'. The added context about ownership and optional persona is helpful but not extensive.

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 'Run a Customer Discovery session: synthetic interviews with AI-generated customer personas who react to your idea', using specific verbs and resources. It distinguishes from siblings like 'run_b2b_diagnosis', 'run_arena_duel', 'run_survival_mode', and 'run_time_machine' by explaining it involves customer discovery interviews with personas, which is unique.

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?

The description explicitly says 'This spends credits and starts a background job', setting expectations about cost and async behavior. It also mentions 'pass an ideaId you own and optionally target a specific persona type', giving clear input requirements. However, it does not explicitly state when not to use this tool or name alternative tools for context.

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