archicad_classify_elements

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

With annotations declaring a non-readonly, non-destructive write, the description adds real value: it discloses the default scope constraint (unclassified elements only) and the recovery path (archicad_undo). It stops short of stating permission requirements or what a partial/ambiguous match does.

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?

Two sentences with zero waste; the core operation and matching rule come first, with defaults and the revert path packed efficiently into the tail.

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 7-parameter mutation tool with full schema coverage and no output schema, this covers the essentials: scope default, matching semantics, and undo path. What it omits — result reporting and interaction with dryRun/overwrite — is minor since those parameters are self-documenting.

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%, so every parameter including rules, dryRun, overwrite, and selectedOnly is already documented in structured data; baseline is 3. The description's example of a rule (Slab on layer '02 PLAZA - Pasto' → 'Terrain') restates the schema's own example rather than adding new meaning.

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 (Classifies) with a broad scope (many elements at once) and the matching mechanism (rules by element type and/or layer), plus a concrete example. It does not explicitly contrast with the sibling SetClassificationsOfElements, which does the same job on explicit elements, so it falls short of the top score.

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?

It implies the default usage context ('by default only those still unclassified') and points at archicad_undo for reversal, which is useful steering. However, it never says when to prefer this tool over SetClassificationsOfElements or when to pass the explicit 'elements' parameter instead of rules.

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