Layout Place

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

With no annotations, the description carries full burden and does so thoroughly. It discloses that coordinates are applied immediately, that block sizes are preserved (not changed), that wires are normalized after movement, and that only lines created in the current session are traced. It even mentions the historical flaw (previously only returned coordinates without moving blocks) and the technical limitation of COM not enumerating page lines. These are precisely the behavioral traits an agent needs to predict side effects.

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 front-loaded with the primary purpose, then expands on critical behavioral details. It is longer than strictly necessary—some historical context (e.g., 'Раньше инструмент только возвращал координаты текстом') could be trimmed without losing essential guidance. However, every sentence contributes to understanding when and how to use the tool, and the structure is logical, so it earns a 4 rather than a 3.

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?

Given the tool's complexity (applies layout, traces wires, interacts with connect), the description covers all necessary aspects: it states the action, the constraints (block sizes fixed, only session lines), the side effects (wire normalization), and the technical limitations. The presence of an output schema reduces the need to describe return values. Nothing critical is missing for an agent to decide when to call it and what to expect.

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?

The input schema already describes both parameters (block_ids and connections) with examples and constraints, achieving 100% schema description coverage. The tool description does not add meaningful semantics beyond the schema—it mentions that position is set before calculation, but that refers to internal state rather than the parameters. It does not explain parameter formats or relationships beyond what the schema already states, so the baseline of 3 is appropriate.

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?

The description clearly states the tool's core action: 'Расставить блоки по слоям без наложений — с применением координат' (arrange blocks into layers without overlaps, applying coordinates). It further clarifies that it actually moves blocks via set_center, unlike previous behavior that only returned coordinates. This verb+resource+outcome statement distinguishes it from siblings like connect (which creates wires) and list_blocks (which enumerates).

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 description provides strong usage context: it is the only place where tracing of lines created by connect in this session is possible, and it explains why (blocks start at (0,0) overlapped). It also notes that lines from outside the session are unavailable. While it doesn't explicitly state 'use this instead of X', the exclusive tracing role and the mention that it applies coordinates serve as clear guidance. There's no explicit when-not-to-use, but the context is sufficient.

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