save_output

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely useful context: the output/ write restriction on save nodes, the COMFYUI_MOUNT_DIR default for dest_dir, and the returned shape. It omits the behavior of the `overwrite` flag, which is the one remaining mutation-risk question.

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 action and the reason, then the two invocation modes, then the return shape — no filler sentences. Slightly dense with parentheticals, but every clause carries information.

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?

An output schema exists so return values needn't be spelled out, yet the description still summarizes {saved_paths, dest_dir}. For a 7-parameter write tool with 0% schema coverage, the only meaningful gap is the overwrite behavior and any permission/auth requirement.

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 carries the full burden and does most of it: prompt_id semantics (relocates every output file), filename with subfolder/type, dest_dir defaulting to COMFYUI_MOUNT_DIR, and dest_filename as a single-file rename. Only `overwrite` is left unexplained.

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 and resource ('Copy a finished render out of ComfyUI's output tree into a folder the caller can reach') and immediately scopes it against the alternative mechanism ('save nodes only write inside output/'). This clearly separates it from read-only siblings like view_output.

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?

Explicitly gives the two invocation modes — pass prompt_id to relocate every output file of a finished job, or an explicit filename plus subfolder/type. It explains why the tool is needed (sandbox reachability) rather than naming a competing sibling tool, so it is clear context without explicit alternatives.

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