Set IFC properties / attributes

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

Annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=true) already signal a mutation, but the description adds substantial context: 'one undo step' (transaction scope), 'Values are written as given (no unit conversion)', per-entry succeeded/failed reporting, and remove semantics. These are behavioral traits the annotations do not convey.

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-loaded with the mutation scope before enumerating kinds and the return shape. It is appropriately sized for a complex multi-mode tool, though the property-kind list and return-shape sentence make it long and more schema-like than prose.

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 complex, annotation-covered mutation tool with no output schema, the description supplies what is missing: transaction behavior, no-unit-conversion semantics, the property-kind vocabulary, and the exact return shape {properties?, attributes?, classificationReferences?} with per-entry success/failure. An agent has enough to call 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?

With only 50% schema coverage, the description compensates well by enumerating the five property kinds and their payload shapes (Single {value}, List {values}, Bounded {lower?, upper?}, Enumerated {values (selected), options}, Table {definingValues, definedValues}) — the trickiest part of the schema — plus the attribute names. It does not explain the undoName, element GUID, or referenceName semantics in prose, leaving some gaps.

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 names specific verbs and resources: adds/changes IFC properties, removes stored properties, sets IFC attributes (Name, Description, ObjectType...), and adds/removes classification references. It explicitly separates itself from set_element_classifications (for Archicad-derived classifications) and get_ifc_data (for reading back), so the agent can distinguish it from siblings without opening schemas.

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 routes the agent to siblings for adjacent tasks — read back with get_ifc_data {storedOnly: true}, and the schema notes set_element_classifications is the path for Archicad classifications. It gives clear context but no explicit when-not conditions; for example, it doesn't state when to prefer set_property_values or set_attribute_property_values over this IFC-specific tool.

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