directory_pull

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

Annotations already declare destructiveHint=true, and the description builds on that by clarifying the destructive scope: unrelated host files are not deleted. It also discloses lock ownership and the required vm_unlock cleanup, which is meaningful behavioral context beyond what the annotations provide.

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?

Two compact sentences with no wasted words. The main action and safety caveat are front-loaded, followed by the lock reminder. Each sentence carries distinct, useful 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?

For a destructive 4-parameter copy tool with no output schema, the description covers purpose, safety boundary, path restriction, and post-condition. The main gap is overwrite semantics, which prevents it from being fully complete.

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?

The description clarifies guest_path as a guest directory and host_path as a host path, but the overwrite parameter is not explained at all. With schema description coverage at only 25%, the description partially compensates but leaves a meaningful parameter undocumented.

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 states a specific action ('merge-copy') with an explicit source (guest directory) and destination (allowed host path), and adds a key safety qualifier: 'without deleting unrelated host files.' This clearly distinguishes the tool from sibling operations like directory_push or file_pull by direction and merge semantics.

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 clear context for when to use the tool: to merge-copy a guest directory to a host path. It also includes a lifecycle precondition ('VM remains locked by this session; call vm_unlock when finished') and an allowed-path restriction. It does not explicitly name alternative sibling tools, which keeps it from a 5.

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