ai_assist

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

With no annotations, the description carries the full burden and does well: it discloses the mutation side effect of task=jam (merges into the current pattern then auto-plays), that suggest output is not auto-executed, that audio analysis is opt-in via includeAudio, and that all three modes share Gemini auth plus rate limiting. It stops short of covering failure behavior and how a jam merge interacts with existing layers of the same type, which matters for a tool that mutates state.

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 content is front-loaded and dense: capability, then per-task behavior, then auth, then alternatives. Minor waste in the trailing issue references (#252) and the inline example, but nothing is buried and no sentence restates the tool name.

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?

For an 8-parameter, three-mode tool with no annotations and no output schema, the description covers purpose, mode semantics, auth prerequisites, side effects, and alternatives — enough to invoke it correctly. The remaining gap is return-value shape for feedback/suggest (what 'creative critique' or 'pattern as text' concretely contains), which has no output schema to fall back on.

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% and every parameter already documents its task binding and defaults, so the schema does the heavy lifting. The description reinforces the task-to-behavior mapping and adds one concrete call example, but supplies no syntax or format detail beyond what the schema already states.

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 names a specific capability (Gemini-backed pattern assistance) and decomposes it into three clearly distinguished modes: feedback returns critique, suggest returns a suggested Strudel pattern as text, jam generates and merges a layer then auto-plays. It also explicitly separates itself from siblings generate_part (non-AI generation) and compose (full compositions), so an agent can route correctly without opening any schema.

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?

Each task variant is given an explicit use condition, including the scope of what it produces and whether it is auto-executed. The closing sentence names two alternative tools and the situations that select them (non-AI generation, full compositions), which is exactly the when-to-use/when-not guidance needed.

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