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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with them while adding real context: it reads the local project folder and recent picks, then returns a brief to fill and a tool-by-tool step list. That tells the agent both the side-effect profile and the shape of the response, which annotations alone would not. It does not say what happens when no recipe ranks well or how large the returned step list can be.

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?

A single front-loaded sentence that opens with the critical routing instruction before describing mechanics — good ordering with no filler. The parenthetical "(flow, mode, named style, calm words)" spends words on jargon that does not resolve into actionable meaning.

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 a 3-parameter, no-output-schema tool, the description supplies the missing return-value information (a brief and a step list naming tools) and the workflow position (call first, then follow the steps). What remains underspecified is the opaque "method" vocabulary and the behavior when the request is ambiguous or no recipe fits.

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 all three parameters (request, product, history) are already documented in the schema. The description gestures at them ("reads their request," "the recent picks") but adds no format, size, or precedence guidance beyond what the schema provides, so the baseline of 3 applies.

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 role — an entry-point planner that parses a design request, ranks recipes, reads project context, and returns a brief plus an ordered step list naming the tools to use. That is far more than a restatement of "start a design." It loses a point because "reads their request the way the method does" and "calm words" reference an internal method the agent has no definition for.

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?

"Call first for any new website, app, screen, or UI" is an explicit routing rule that places this ahead of siblings like pick_direction, get_recipe, or browse_library. It does not state a when-not condition (e.g., resuming existing work or iterating on a page), so it stops short of full when/when-not coverage.

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