Delete service files

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

Annotations already declare destructiveHint=true, but the description goes far beyond: no recycle bin, recursive delete stays within the path's file system and never follows links, refuses / and top-level/OS directories, refuses execution-equivalent targets (authorized_keys, cron, sudoers, etc.), documents required scopes (files:manage, vm:files:write), availability gating (agent_update_required, feature_disabled) and a 423 response for 2FA-locked servers.

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 destructive action and its scope, then layers constraints. Dense but nearly every sentence carries operational value; the error-code and availability detail is long but justified for an irreversible operation.

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?

With no output schema, the description still tells the agent it may return an operationId (via waitSeconds) and enumerates the failure modes and reason codes it must surface verbatim. Complete for a destructive, permission-gated file operation.

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 67%, and the description adds real meaning for recursive (needed for non-empty dirs), confirm (approval semantics), confirmSystemPath (OS-path approval) and waitSeconds (default 60 here). Minor tension: the schema documents waitSeconds default as 30, which the description does not reconcile.

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+resource ('Permanently delete files or directories'), scopes it (1-100, no recycle bin) and disambiguates from sibling file tools such as move_service_file and write_service_file. The permanent, irreversible nature is stated up front.

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?

Explicit when-to-use conditions: recursive=true is required for non-empty directories, confirm=true only after the user approved exactly these paths, confirmSystemPath=true only after explicit OS-path approval. It also states when-not: relay unavailability reasons verbatim and never work around them.

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