use_sample

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

Annotations already cover idempotentHint=true, destructiveHint=false, and readOnlyHint=false. The description adds that it sets an environment variable (DEMO_TRAVEL_SAMPLE_DIR) and writes a catalog UI in beer mode, and that beer mode uses 'no LLM; find→get'. This gives some behavioral color beyond annotations. But it doesn't disclose side effects like directory creation, network cloning, or permission needs. Since annotations carry the safety profile, a 3 is appropriate.

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 description is compact and uses line breaks to separate the two sample modes and the project_name note. The most important parameter (sample) is front-loaded. There is no wasted prose, though some jargon ('Direct catalog', 'find→get') could be clearer.

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?

With an output schema present and idempotency annotations, the description covers the basic invocation path. However, given 5 parameters with zero schema descriptions, the description should explain all parameters to be fully complete. It also doesn't reference sibling tools to help the agent choose between them. For a tool with two main modes, it is adequate but not comprehensive.

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 the 'sample' parameter's allowed values ('travel'/'beer') and their distinct behaviors, and it documents 'project_name's default behavior. However, it leaves 'parent_dir', 'sample_dir', and 'clone_if_missing' completely unexplained, which is a significant gap for full parameter semantics.

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 states the tool sets up UI samples for either 'travel' or 'beer' templates, with concrete actions ('locate/clone demo_travel_sample' vs 'write demo_beer_sample Direct catalog UI'). It distinguishes two modes based on the 'sample' parameter. However, the initial phrase 'UI sample: travel clone or beer Direct template' is cryptic and lacks a clear overall statement of function, missing the clarity of a top-tier explanation.

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?

The description provides some conditional guidance ('sample=travel' vs 'sample=beer') and notes that 'Extra travel-only phases stay on travel_golden_path (travel toolset)', implicitly steering extra travel work to a sibling toolset. However, it never explicitly states when to prefer this tool over siblings like scaffold_app or start_project, nor lists exclusion conditions. Usage is implied rather than fully explicit.

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