Call a service

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the mutation risk is covered. The description adds genuinely useful context beyond them: the write-enable gate, domain denylist blocking, and that the response returns the changed entities.

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?

Two sentences, front-loaded with the core action and followed by the gating constraint. The parenthetical example is long but earns its place by demonstrating parameter structure; nothing here is filler.

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?

Without an output schema, the description responsibly states what comes back (the entities that changed), and it surfaces the write gate and denylist behavior an agent must know before invoking. Nested target/data objects are covered by the schema, so remaining gaps 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 100%, so the baseline is 3, but the inline example maps domain/service/data/target to a realistic brightness_pct call and shows the target selector shape, adding practical meaning beyond the field descriptions.

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 (call) and resource (Home Assistant service) and immediately shows the exact shape of an invocation with a concrete working example. An agent can tell this is the generic service-dispatch tool, distinct from siblings like ha_update_entity or ha_fire_event, without opening the schema.

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 gives important preconditions ('refused unless writes are enabled', 'blocked for denied domains') but never says when to prefer this over alternatives such as ha_update_entity, ha_trigger_automation, or ha_fire_event. Usage is implied by the example rather than explicitly scoped.

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