use_sample

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

Annotations only give write/idempotent/open-world hints; the description adds substantial behavior the agent could not otherwise know — it clones repos, sets env vars (DEMO_TRAVEL_SAMPLE_DIR), writes a gitignored mode-600 config.json, requires an LLM key, asks before writing when no Zeus URL is stored, and that a 401 'stays red'. This is rich disclosure, though it is buried in prose rather than surfaced.

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?

This is a dense, unsegmented wall of ~300 words of run-on clauses with no headings, bullets, or clear front-loading; variant-specific behavior is interleaved with unrelated details (photo download paths, review doc keys, port numbers). Almost every sentence carries information, but the structure actively impedes scanning.

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 complex, open-world tool that clones and writes files, the description covers prerequisites, side effects, credential handling, and edge cases well, and an output schema exists so return values need not be explained. Remaining gaps (clone_if_missing/sample_dir behavior) are minor.

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% and there are no enums, so the description must carry the load — and it largely does: it enumerates valid sample values and aliases, explains parent_dir clone behavior, and gives project_name defaults per sample. clone_if_missing and sample_dir are only obliquely covered, keeping it short of a 5.

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 opening line names the resource (UI samples) and enumerates the variants (travel, beer, catalog, demo_yelp) with aliases, but never states the core action in a single clear verb — the agent must infer 'locate/clone/write' from scattered clauses like 'write demo_beer_sample catalog UI'. Differentiation from siblings is partial (e.g. 'Extra travel-only phases stay on travel_golden_path'), so the purpose lands but only after reading the whole block.

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?

Usage is spelled out per variant (sample=travel vs beer vs catalog vs demo_yelp vs bare yelp) and it explicitly excludes misuse: 'Do not write a replacement or copy demo_beer_sample', 'Do not pass a password', 'Bare sample=yelp stays the multi-agent handoff'. It stops short of routing against named sibling tools like scaffold_app or start_project, so it isn't a full 5.

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