List registry items

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds the projection behavior of `fields` (shrinking results) which is genuinely useful context, but says nothing about result truncation, the 100-item default/500 cap, or ordering — the behaviors an agent would most want to know for a listing tool.

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 scope and resource list, no filler. The `fields` example earns its place by making the projection concrete, though it is slightly verbose for what is essentially a parameter hint.

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 simple, read-only, four-parameter listing tool with full annotation coverage and no output schema, the description covers essentially everything needed to invoke it: what registries exist, how filtering works, and how to shrink results. The remaining omissions — relation to list_areas and the behavior of `max_items` — are minor rather than blocking.

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 50%: `query` and `fields` are documented in the schema, while `registry` and `max_items` are not. The description restates the filter and gives a concrete `fields` example that clarifies intent beyond the terse schema text, and its enumeration mirrors the `registry` enum. But `max_items` (default 100, cap 500, and what happens when exceeded) is never explained, leaving a real gap.

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 (list) plus the exact resource set (areas, floors, labels, devices, entities, zones from the Home Assistant registries) and mentions the optional text filter. An agent knows exactly what it gets. However, it never distinguishes itself from the close sibling list_areas (registry='area') or search_entities, so the boundary with siblings remains ambiguous.

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 sentence 'Use fields to keep results small, for example fields ["entity_id","name","area_id"]' is real guidance, but it is parameter-tuning advice rather than when-to-use guidance. There is no statement about when to prefer this over list_areas or search_entities, nor any exclusion conditions; usage is only implied by the enumeration of registry types.

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