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

Annotations already provide safety and idempotency hints. The description adds meaningful behavioral context beyond them: the special 'skip' semantics, the 'last round' nature, and that the reply carries answer_required=false with no further questions. This helps the agent understand conversational state changes.

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 concise sentences, front-loaded with the core action, followed by the special case and the final-round behavior. Every sentence adds information without repetition or 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?

The description covers the tool's purpose, how to express the skip case, the surrounding conversation flow, and what response to expect. With annotations covering safety and idempotency, nothing essential is missing for correct selection and invocation.

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 100%, so the schema already documents draft_id and answers thoroughly. The description adds only a clarifying nuance about 'whatever Mitosis thinks best' for the skip answer, but largely restates what the schema already says. 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?

The description states a specific action and object: 'Records the user's answer to the questions from cortex_create_goal, keyed by question id.' It clearly differentiates from siblings like cortex_accept_goal and cortex_ask by framing this as the answer step that follows the goal-creation question round.

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 gives clear sequential context: this tool is used after cortex_create_goal, and it is the final round because 'Mitosis asks about a goal once.' It does not explicitly name alternative tools to avoid, but the temporal context is enough to guide selection.

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