Create labels

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

Annotations already declare the operation is a write (readOnlyHint=false) and non-destructive, but the description adds critical behavior beyond that: returns [{guid, type} | {error}] in input order, one failing item does not stop others, parent and class of an existing label cannot be changed (delete and recreate required), and active-window placement rules including that a 3D window cannot hold 2D elements.

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?

The description is a single dense paragraph but front-loaded with the core action and organized logically from basic purpose to associative/independent details, leader mechanics, label class differences, placement context, and return behavior. Every sentence adds value for this complex tool, though bullet points or clearer segmentation would improve scanability.

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 tool with a large nested input schema, no output schema, and moderate complexity, the description covers all essential context: how to create associative vs independent labels, leader construction, text vs symbol label requirements, active-window constraints, error handling, and post-creation modification/readback. Nothing critical for correct invocation is missing.

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?

With 100% schema description coverage, the schema already documents each parameter. The description still adds meaningful semantics: explains the leader geometry sequence (begin arrow point -> middle -> end text), clarifies when to use text vs runs, notes that omitting 'end' on associative labels uses Archicad's default position, and links symbol labels to libraryPart and gdlParameters with search_library_parts. It does not cover every field (e.g., justification, renovationStatus), but key relationships are made explicit.

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+resource ('Places labels') and immediately distinguishes associative vs independent labels, leader lines, and text vs symbol label classes. It differentiates from sibling create_texts by noting shared style fields while clearly positioning this tool as the label creator.

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?

Provides clear context for when to use this tool: describes where labels land (active window, floor plan vs section/elevation), how to find library parts for symbol labels, and how to later modify or read them back. However, it lacks explicit when-not or direct alternatives (e.g., 'use create_texts instead when you need plain text without a leader').

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