files_delete_file

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

With no annotations supplied, the description carries the full behavioral burden for a destructive operation. It correctly discloses the non-recursive scope, but says nothing about permanence/irreversibility, behavior when the path does not exist, sandbox-root confinement, or permission requirements.

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?

A single short sentence, front-loaded with the verb and immediately qualified by the key constraint. No filler or redundant restatement of the tool name.

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 need not be described, and the tool is a simple one-parameter operation. However, for an irreversible file removal with no annotations, the missing details on permanence, error cases, and path resolution leave a real gap.

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% for the single parameter, and the description adds nothing about what "path" means — whether it is absolute, sandbox-relative, whether subdirectories are allowed inside it, or what conventions the sibling file tools use. The one parameter it has is essentially undocumented everywhere.

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?

"Delete a file ... from the sandbox" gives a specific verb plus resource, and "(never a directory)" bounds the scope in a way the name alone does not. It does not name any sibling or alternative, so it falls short of full differentiation, but the operation is unmistakable.

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 parenthetical clarifies one exclusion (directories are out of scope), which is meaningful when-guidedance. It gives no positive context about when to prefer this over, say, overwriting via files_write_file, and no prerequisites or state expectations.

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