Compose styles from snippets

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely new behavior: property-level merge order (later entries override earlier for the same category/property), the explicit 'makes no call to Home Assistant' guarantee, and the unknown_snippet error shape with its known list.

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 action, then cleanly separated Use when / Returns / Errors blocks. Every sentence carries distinct information; nothing is redundant 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?

For a pure-computation composer with full schema coverage and an output schema, the definition covers purpose, usage condition, merge semantics, and error behavior. An agent has everything needed to select and invoke it correctly; the Returns line is mildly redundant given the output schema but not harmful.

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 baseline is 3. The description goes beyond the schema by spelling out merge precedence between ordered snippet_names and the trailing extra object, which the schema only hints at, adding real semantic value on how the inputs interact.

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 (compose) and resource (a styles object from built-in snippets plus overrides), and names the underlying STYLE_SNIPPETS source. It is clearly distinguishable from sibling style tools like card_builder_get_style_snippet or card_builder_list_style_presets.

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 'Use when' clause gives concrete context — assembling a block's styles/dz_styles from reusable presets rather than hand-writing the full envelope — and points at card_builder_list_style_snippets as the source of names. It stops short of naming an explicit alternative tool to use when the condition is false, so it is clear but not fully routing.

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