undo

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

No annotations exist, so the description carries full burden. It discloses the undo-step semantics and the graphical-Houdini requirement, which are non-obvious behavioral constraints. However, it doesn't explicitly state that undo is destructive or that it changes scene state, though that is implied by the verb.

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?

Extremely concise: first line states the action, second paragraph explains granularity and environment, third lists args. No filler, front-loaded purpose.

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 simple undo tool with one optional parameter and no output schema, the description covers all necessary information: action, scope, environment requirement, and parameter explanation. Nothing essential is missing.

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 has 0% description coverage, but the description explains the only parameter 'steps' with meaning and default value. It also mentions 'ctx' as an argument, though that is not in the schema, which is a minor inconsistency but doesn't harm usability.

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 exactly what it does: undo last change(s) in Houdini. Clarifies granularity (one undo per tool call) and gives concrete examples (reverses build_network or set_parameters). This distinguishes it from other mutation tools and even from redo by explaining its scope.

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?

Provides context that it works only in graphical Houdini (not hython), which is a clear exclusion condition. It also implies when to use it (after a mutation tool call) via the undo-step explanation, but doesn't explicitly mention alternatives like redo or revert_parameter.

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