ifc_patch

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

With no annotations, the description carries the full burden and does disclose important behavior: rebuilding the model into a new file object, the file-replacement requirement, and why blender mode refuses these recipes because Blender's objects would point into the discarded file. It does not discuss reversibility or whether a subsequent save is required, but the key behavioral edge cases are covered.

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: one purpose sentence, a recipe list, then two short paragraphs for constraints. Every sentence earns its place without redundancy.

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 tool with three parameters, multiple recipes, and mode-dependent behavior, the description covers the supported recipes, the args contract, and the important file-replacement constraint. It does not explicitly state whether the in-memory model is mutated and must be saved afterward, but the provided information is sufficient to call the tool correctly in most cases.

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 compensates by explaining that `args` uses recipe-defined parameter names and that a wrong name is answered with the accepted list and defaults. It also clarifies the conditional role of allow_file_replacement for the two rebuilding recipes. The recipe list adds meaning that the bare schema lacks.

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 ('Run an ifcpatch recipe over the whole model') and then enumerates the supported recipes. This clearly distinguishes the tool from sibling editing/query tools by stating exactly what it operates on.

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 gives concrete usage conditions: which recipes need allow_file_replacement=true in standalone mode and that those recipes are refused in blender mode. It does not name alternative sibling tools for different use cases, but the when-to-use and when-not-to-use guidance is clear enough.

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