Merge walls

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

With destructiveHint=true already indicating destructive behavior, the description goes further: the longest wall keeps its id and build, the others are deleted, doors and windows stay, gaps close, and the reply names the remaining id. This adds substantial behavioral context beyond the annotation and accurately aligns with the destructive hint.

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 main purpose and then covers side effects efficiently. The last sentence ('Straight walls on one storey whose centerlines run inside one another; the reply names the id that remains.') is slightly clunky and could be integrated into the main clause, but every sentence contributes meaningful information.

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 destructive, single-parameter tool, the description covers the operation, side effects on walls and openings, gap behavior, and output essence. Since an output schema exists (per context), the description need not detail the return structure. It is complete enough for correct invocation, though it could briefly mention error cases (e.g., non-collinear walls).

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 schema description for 'ids' already states 'in order along the line they make,' giving 100% coverage. The tool description reiterates the order implicitly but adds no new parameter-specific semantics beyond the schema. Baseline 3 is appropriate here.

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 and resource ('Join walls that run along the same line into a single wall') and immediately gives concrete scenarios (partition interruption, imported segments, drawn twice) that distinguish it from related tools like split_wall and delete. This is not a tautology; it tells an agent exactly what the tool accomplishes.

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 clear contexts for use ('the wall a partition interrupted, a stretch imported as many segments...') and imposes a condition ('Straight walls on one storey whose centerlines run inside one another'). However, it does not explicitly mention the alternative split_wall or state when merging should not be used, so it falls short of fully explicit when/when-not guidance.

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