ue5_execute_command

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

With no annotations, the description carries the behavioral disclosure burden. It usefully notes that arguments are 'less validated' and unregistered commands 'fail-loud', which are meaningful safety signals. However, it does not explicitly warn about potentially destructive side effects (delete_asset, set_actor_transform, etc.) or state permission requirements, leaving the agent to infer mutability from the command list.

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?

The description is front-loaded with purpose and usage guidance before the long command list, which is necessary for a valid invocation. The bilingual repetition ('白名单命令透传（专用工具未覆盖时使用）') is redundant but not harmful. Overall each sentence serves a role, though the list makes it unavoidably lengthy.

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 generic tool covering 72 commands with no output schema, the description provides the essential context: role, when to use, the full valid command set, and failure behavior. It lacks a description of the return format and per-command parameter specifics, but given the breadth and the thin schema, it is reasonably complete. The safety profile is less full without annotations, though the 'less validated' caveat partially covers it.

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. The description adds substantial value by enumerating the complete command whitelist, effectively providing all valid enum values for `command`, and clarifying that `params` is the command arguments object. This goes beyond the schema's terse field descriptions.

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 opens with 'Escape hatch: run any whitelisted bridge command by name', a specific verb-resource pairing that immediately conveys a generic execution role. It distinguishes itself from dedicated siblings by stating 'Prefer the dedicated tool whenever one exists' and listing the full 72-command surface, making its scope 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?

Explicit guidance is provided: 'Prefer the dedicated tool whenever one exists for the operation; this generic entry point is the last resort.' It further explains that arguments are less validated and unregistered commands fail loudly, giving the agent clear criteria for when to invoke this tool versus its siblings.

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