open_image

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

With no annotations, the description carries the full burden and does: it discloses the visible side effect (a viewer window on the user's screen), that the image is never returned to the model, that the result is only a short text confirmation, that headless machines yield a note rather than an error, and that the file on disk is never modified.

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 trigger/gating rule follows immediately. The gating rule is partially duplicated by the path parameter's schema description and a few clauses (Linux viewer specifics, restating the no-modification guarantee) could be trimmed without loss.

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?

Covers everything an agent needs for a one-parameter, no-output-schema tool: what it does, when it is permitted, what it returns and does not return, error behavior for bad paths, and the path resolution model. No meaningful gap remains.

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 coverage is 100%, so the baseline is 3, but the description adds genuinely new semantics: paths resolve relative to MEMDRIVE_ROOT, absolute paths are only accepted inside the root, and out-of-root or non-image paths are rejected. It stops short of describing other edge cases, but the added value is real.

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 (open an image file from the MemDrive library) and names the exact mechanism (OS default viewer, full original quality). It also distinguishes itself from read_file, which is the sibling an agent would otherwise confuse it with.

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 explicit when-to-use triggers with example phrasings, explicit when-NOT-to-use rules ('NEVER call after read_file, save_file, or any other tool call'), and the alternative to use instead (read_file for in-conversation viewing). Nothing is left to inference.

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