generate_feedback_topics

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

With no annotations, the description carries full responsibility for behavioral disclosure. It explicitly states the interactive prerequisite (ask user for focus), the conditional behavior (skip generation for 'awareness'), and the generation rule (3-5 questions weighted toward focus). This goes beyond a simple mutation statement.

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 well-structured: a one-sentence summary, an 'IMPORTANT' call-out, a numbered list of focus options, and a concise conditional rule. Every sentence earns its place; the list is necessary because it provides the exact wording to present to the user.

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 interaction flow, focus handling, and generation guidance. However, it is slightly ambiguous whether the tool itself generates the topics or expects the agent to populate the 'topics' parameter, which is part of the input schema. This missing explicit clarification prevents a perfect score.

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?

Even though schema coverage is 100%, the description adds essential semantics: it maps the user's answer to the 'focus' enum values, explains the 'awareness' special case (skip topics, set brief), and clarifies that topics should be weighted toward the focus theme. This is meaningfully beyond the schema descriptions.

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 opens with a specific verb and resource: 'Auto-generate feedback questions for a prototype based on what was built.' This clearly distinguishes it from sibling tools like get_feedback (retrieval) and triage_feedback (categorization).

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 provides clear context and a step-by-step process: ask the user for focus, present options, use the answer as the 'focus' parameter, and generate 3-5 questions. It does not explicitly compare against alternatives, but the workflow implies when this tool should be used.

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