design_screens_skeleton

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

With no annotations, the description carries the full burden and does reasonably well: it discloses that write=True persists to <app>/design/screens.json, that it refuses to replace an existing file unless overwrite, and it enumerates content rules (no fake stats/reviews, spin wheel, rating or notification prompts). The default write=false preview behavior is only implied, not stated outright.

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?

Front-loaded with the core artifact and purpose, and every clause earns its place (behavioral rules, write/overwrite semantics). It is denser and more run-on than ideal, but there is no padding.

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. The description covers the conditional content source, the content constraints, and the persistence semantics, which is nearly everything an agent needs for this three-parameter generator; only the non-writing default mode remains under-specified.

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%, so the description must compensate. It explains write=True (persists) and overwrite (permits replacing an existing file), and the <app>/design/screens.json path implies app_dir is the app directory. All three parameters get at least implicit meaning, but write=false is not explicitly described as an in-memory preview.

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 and artifact: it builds a STRUCTURAL skeleton for design/screens.json. It distinguishes itself from the authoring step by noting 'the look is authored in Claude Design, not here,' which helps separate it from siblings like design_generate. The purpose is clear, though the sentence structure is convoluted enough that it takes a second read.

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?

It distinguishes the two input regimes (with a brief vs without) and hints that visual authoring happens elsewhere, but it never explicitly states when to call this versus design_generate or the other design_* siblings by name. Usage is implied rather than prescribed.

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