undo

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

With no annotations the description carries the full burden and it delivers the most valuable behavioral fact: atomicity per tool call ('however many nodes it touched'), plus a hard environmental precondition (graphical Houdini only). It omits failure behavior when the undo stack is empty and whether the operation is opt-in per session, keeping it short of a 5.

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?

Front-loaded with the core behavior, then the granularity insight, then the precondition — good ordering with no filler prose. The trailing 'ctx: MCP context' arg note is boilerplate for a parameter that is not even in the schema, a small amount of wasted text.

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 one-parameter mutation tool with no annotations and no output schema, the description covers what the agent most needs: the scope of an undo step, the environment requirement, and the steps parameter. Only edge-case behavior (empty history, interaction with redo) is left undocumented.

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 must compensate, and it does: 'steps: How many steps to undo (default 1)' explains the parameter's meaning and default beyond the bare integer schema. It does not clarify the upper bound or what happens when steps exceeds available history.

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 (undo) and resource (the last change(s) in Houdini), and pins down the granularity: one tool call equals one undo step no matter how many nodes it touched. That scope statement makes it unmistakable against the sibling redo, which reverses in the other direction.

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?

Gives a concrete usage condition and a clear when-not: it explicitly names the example operations it reverses (build_network, set_parameters) and warns that a graphical Houdini session is required because hython keeps no undo history. It never explicitly points at the redo sibling for the opposite action, so the routing guidance is not fully exhaustive.

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