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

With no annotations, the description carries full disclosure: it covers validation checks (floor area, overlaps, blocked areas, 0.9 m path), coordinate units and origin, the 5 cm grid snapping for spots, the fact that placement pieces are never nudged and are rejected if they stick out or overlap, and persistence behavior (nothing saved on beispiel-wohnzimmer). This is far beyond a bare 'places furniture' statement and gives the agent an accurate behavioral model.

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?

A single dense paragraph front-loads the action and output, then the three-mode decision, then the universal constraints and coordinate conventions. Every sentence adds decision-relevant information, with no filler or repetition of the 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?

For a 9-parameter tool with no output schema and no annotations, the description covers the essential decision framework (which mode to send), key output shape, geometric constraints, units/origin, and the authentication caveat. Nothing critical is missing for an agent to select and invoke it correctly.

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 baseline is 3, but the description adds critical cross-parameter semantics: the three mutually exclusive modes, their precedence ('Prefer spots'), and the guardrail never to invent x, y, rot. It also clarifies the measurement conventions for x/y as meters to the piece center from the room's top-left corner, which is unambiguous and supplements the per-parameter schema text.

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 ('places furniture') and enumerates the return payload (image plus placed, rejected, issues, image_prompt), which distinguishes it from siblings like move_furniture and check_plan. The first sentence already conveys the tool's core action and output.

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 instructs to send exactly one of spots, placement, or wish and gives preference rules with conditional triggers ('Use placement only when the user gives exact positions; never invent x, y or rot'; 'Use wish only when the user describes the room without naming pieces'). It also notes the key requirement vs. the free beispiel-wohnzimmer project, covering both when and when-not scenarios.

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