create_wall_2d

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

With no annotations, the description carries the full behavioral burden. It does well by disclosing that the wall is drawn as a closed outline, that overlapping/touching walls are fused, that this fusion should happen before doors/windows, and that the tool returns corners, length, thickness, and outline names. It does not explain the fit_view parameter's behavior, so it is not fully exhaustive, but it is substantially transparent.

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 compact and front-loaded: the first sentence states the core function, followed by concise parameter notes, a timing warning, and a return summary. Every sentence adds value and there is no filler.

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 5-parameter creation tool with no annotations, the description is nearly complete: it covers units, layer, geometry semantics, defaults, merge behavior, timing constraints, and return values. The missing fit_view behavior and lack of any mention of errors or coordinate system leave a small but real gap, so it is not a 5.

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 0%, so the description must compensate. It clarifies that start/end are [x,y] points on the wall axis, explains the merge default and its fusion behavior, and gives the effective default thickness of 200 mm. The only parameter left unexplained is fit_view, whose schema default is true but whose behavior is never described.

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 opens with a specific verb ('Draw'), a specific object ('one straight wall as a closed outline'), and a target layer ('murs' with mm units). The phrase 'one straight wall' distinguishes it from sibling tools like create_wall_loop and create_walls_3d, so an agent can tell what this tool is for.

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 gives useful context by warning that merging should happen before placing doors/windows, and by explaining when merge will not apply. However, it never explicitly says when to choose this tool over siblings such as create_partition_2d or create_wall_loop; the differentiation is only implied by 'one straight wall'.

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