Create texts

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

Goes well beyond what annotations provide: describes partial-failure semantics ('one failing item does not stop the others'), the return shape [{guid, type} | {error}] in input order, the paper-mm scaling behavior of text size (unless fixedSize), the multilingual/rich-text capability, and the round-trip with modify_elements. This is exactly the behavioral context an agent needs when annotations only say readOnly=false and idempotent=false.

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 long opening sentence is dense but front-loads the core purpose plus field inventory, and subsequent sentences are each functional (placement context, return shape, round-trip). Minor redundancy in listing style fields and re-stating 'get_attributes {type: Font}' which also appears in the schema, but nothing is wasted.

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 complex, high-parameter-count creation tool with no output schema and only coarse annotations, the description covers purpose, placement constraints, failure semantics, return shape, and follow-up operations. An agent has everything it needs to invoke this correctly; the only minor gap is the absence of an explicit alternative-selection rule.

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 baseline is 3, but the description adds real semantic value beyond the schema: it explains the mm-on-paper scaling (with fixedSize caveat), the '\n' newline convention, rich-text runs with per-run styling, the get_attributes path for fonts, and the position-anchor relationship. The 'Change them later with modify_elements using the same field names' note is useful cross-tool parameter guidance.

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?

Opens with a specific verb+resource ('Places text blocks (Archicad 'Text' tool)') and enumerates the fields it supports, distinguishing it from siblings like create_labels, create_dimensions, and create_elements. An agent can identify exactly what this tool creates without checking its 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?

Explicitly states the context constraint: elements go into the active window's database, with per-window rules (storyIndex on floor plan, otherwise section/elevation/detail/worksheet/layout, and 3D windows cannot hold 2D elements). It names modify_elements and get_element_details for follow-up operations, but doesn't call out when to pick this over related create_* tools like create_labels or create_hotspots.

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