Update area

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

Annotations already declare destructive/idempotent, but the description adds material context: partial-update semantics ('only the parameters you pass are sent'), the immutability of area_id and its effect on assignments, the WS endpoint, and that previous values are not returned. Limits section explicitly discloses that aliases replaces the whole list and that icon/floor cannot be cleared — precisely the kind of destructive edge case an agent needs before calling.

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 action, then labelled sections (Use when / Not for / Returns / Errors / Limits) that are scannable rather than prose. Each block carries distinct information; nothing is redundant with the title or schema.

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?

Covers the full decision surface for a destructive, partial-update mutation: what changes, what doesn't, empty-field error, unknown id / duplicate name failures, and non-reversibility of alias replacement. Output schema exists but the description still names the returned dict keys, which is helpful rather than wasteful.

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 schema already defines each field; the description still adds replacement-vs-merge semantics for aliases and the fact that icon and floor cannot be cleared here even though the schema allows null. It stops short of restating per-field formats, which is reasonable.

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 and resource ('Rename an area or change its icon, floor or aliases') and enumerates exactly which area attributes it touches. An agent can tell it apart from areas_create_area, areas_delete_area and devices_update_device without consulting 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?

Explicit 'Use when' (renaming a room, moving floors) and 'Not for' clauses that name the correct alternative tool for each excluded case (areas_create_area, devices_update_device, entities_assign_entity_to_area). No routing decision is left to inference.

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