press_button

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

The description discloses critical behavioral traits: the call holds until the callback returns with no deadline, dialog-opening callbacks block the main thread, errors/warnings are from the last cook unless cook=True, and has_script_callback is False for built-in buttons that still do work. This goes well beyond what annotations (none provided) would cover.

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 dense but well-organized, front-loading the core action and then layering caveats. Every sentence adds value, though the paragraph on errors/warnings and has_script_callback is somewhat long and could be tightened. Still, it's efficient for the complexity it covers.

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 no annotations and no output schema, the description is remarkably complete. It covers the action, blocking behavior, error semantics, the cook parameter's effect, and the distinction between script callbacks and built-in buttons. An agent has everything needed to invoke it correctly and interpret results.

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. It explains node_path (node that owns the button), parm_name (the button parameter's name), arguments (optional kwargs with type constraints), and cook (cook after press so errors describe the result). This fully covers all 4 parameters with meaning beyond the schema's bare names.

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 clearly states the tool presses a button parameter on a node and reads errors/warnings afterwards, with concrete examples (Stash Input, Reload Geometry, Build). It distinguishes itself from related tools like write_cache/start_render by explicitly naming them as alternatives for Save to Disk or render actions.

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?

The description provides explicit when-to-use guidance: use write_cache/start_render for Save to Disk or render operations instead. It also warns about callbacks that open dialogs blocking Houdini's main thread, advising to read the button's script first if in doubt. This is strong usage guidance.

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