Create Text

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

Annotations declare readOnlyHint=false, correctly flagging this as a mutation operation, and the 'Create' verb is consistent with that — no contradiction. The description adds only the DTEXT/TEXT primitive clarification, which carries mild behavioral weight (single-line semantics), but discloses nothing about side effects such as whether omitted color/layer fall back to current drawing settings or which space the entity is created in. With annotations covering the basic safety profile, the added context is thin but acceptable.

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?

Eight words in a single sentence, with the verb, the key differentiator ('single-line'), and the primitive mapping all front-loaded. There is zero filler and nothing duplicating schema fields. This is exemplary sizing for a simple create tool.

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?

The tool is a simple 7-parameter create operation; the schema documents every parameter with defaults and an output schema exists, so the description's minimalism is not costly. The main omission is explicit routing to entity_create_mtext for multi-line text, which the agent must infer from the 'single-line' qualifier alone. For this complexity level, the definition is largely complete with that single usage gap.

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% — x, y, text, color, layer, height, and rotation all have meaningful descriptions and defaults in the schema itself, so the description need not repeat them. The description adds no parameter-level detail, but at this coverage level the schema carries the burden fully. Baseline 3 applies.

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 (create), a resource (text entity), and the crucial qualifier 'single-line,' which distinguishes it from the entity_create_mtext sibling. The parenthetical '(DTEXT/TEXT)' maps the tool to the underlying CAD primitive, removing ambiguity about which command family this invokes. It stops short of explicitly naming entity_create_mtext as the alternative, which would earn a 5.

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 'single-line' qualifier implies this tool is for simple text labels, implicitly excluding multiline/paragraph text, so an agent can infer basic usage context. However, the description never explicitly says when to choose this over entity_create_mtext or other entity_create_* siblings, and provides no when-not conditions or alternative routing. The usage guidance is implied, not stated.

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