icon_generate

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

With no annotations, the description carries the full burden and does disclose meaningful traits: it costs money and is gated behind approval, it writes to a specific artifact directory, and it produces reference drafts rather than shippable assets. It omits rate-limit/auth details, but the cost and non-destructive-vs-shipping behavior are the operative facts.

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?

Two dense sentences, zero filler, with the most consequential constraint (opt-in/cost/approval) front-loaded before the output-destination and sibling-routing details.

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?

An output schema exists, so return values need not be explained, and the description covers the action, destination, and gating. The remaining gap is parameter meaning: an agent still cannot tell what app_dir, concept, or extra should contain.

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 0% across 4 parameters, and the description never explains app_dir, concept, extra, or allow_external_generator. 'fal raster' only loosely hints at the external-generator flag, so the parameters are essentially undocumented in both schema and description.

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?

States a specific verb+resource with output destination: generates a fal raster DRAFT into design/icon_drafts/ for the Claude Design icon board. It also names the sibling icon_install as the tool that ships the real icon, so an agent can distinguish draft generation from installation.

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?

Gives an explicit precondition ('OPT-IN ONLY (spend → approval)') and an explicit boundary ('Never installs an icon — the shipped icon comes from Claude Design (icon_install)'), which routes the agent to the correct sibling for shipping. It stops short of describing when inside the pipeline this step should be invoked.

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