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

Annotations only declare readOnlyHint and openWorldHint; the description adds materially important behavior not in the annotations — responses are paged at roughly 32KB per section, a header flag more:true signals truncation, and the agent must continue with offset=<next_offset> rather than restarting. That paging disclosure is exactly the kind of operational context that prevents a subtle failure mode.

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-loads the core action and the critical 'fetch BEFORE authoring your UI' sequencing, with paging last. Some promotional framing ('the single biggest lever for app quality', 'real stunning apps') is not strictly load-bearing, and the parenthetical about SDK components is dense, but no sentence is wasted.

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 read-only fetch tool with no output schema, the description compensates fully: it names every returned file, describes the index-listing response, and explains the paged response envelope (more flag, next_offset). An agent has everything needed to call it correctly and resume paging without guidance from elsewhere.

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 coverage is 100%, so the enum and field meanings are already covered, but the description still adds value: it explains that archetype='index' is a listing mode rather than a real app, names the valid archetype choices, and describes offset as a 'next section' pointer tied to the more flag. max_bytes is left unexplained in the prose, though the schema covers it adequately.

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 resource ('Fetch a COMPLETE, production-quality reference app') and enumerates exactly what is returned (schemas.py + config.py + setup.py + ui/app.js). It also distinguishes itself from adjacent concepts by noting the SDK components catalog is 'optional, not what these mirror', separating it from the sdk_* and build_get_skills siblings.

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 workflow: start with archetype='index' to list options, pick the closest archetype by name, and fetch 'BEFORE authoring your UI'. It also names the alternative path (file= for a single file) and warns against re-fetching from offset 0, which is a when-not-to-do-it instruction.

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