fgui_adjust_depth

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

With no annotations, the description carries the full burden and does substantial work: it discloses that the operation returns the complete before/after order, that it does NOT enter the Agent undo stack (a non-obvious and consequential trait), that save writes the entire current document rather than just this object, and that external_reload requires save=True. It stops short of stating permission requirements or failure modes beyond the bounds/group-block constraint.

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?

Four compact lines, front-loaded with the action and target, then constraints, then side effects. Dense but every clause carries information; the only cost is heavy jargon compression ('不进 Agent 撤销栈') that may read as terse to an unfamiliar agent.

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 spelled out, and the description wisely still notes the before/after ordering. The remaining hole is target resolution across three identifier parameters, which for a 7-parameter mutation tool is a meaningful gap that neither structured field fills.

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%, so the description must compensate, and it does for index (0-based, 0 = bottom-most), save (whole-document save), external_reload (requires save=True), and implicitly verify (reopen to confirm persistence). However, the three target selectors object_id, object_name, and object_path are never mentioned, leaving the most important question — how the target object is identified and whether the three are mutually exclusive — undocumented in both schema and description.

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 names a specific verb and resource ('move an unlocked, ungrouped object under a root component to absolute depth index'), which is far more precise than the tool name alone. It does not explicitly contrast itself with siblings such as fgui_insert_object or fgui_create_group, so an agent must infer the boundary from the 'ungrouped object' qualifier.

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?

Applicability is clearly bounded: the object must be unlocked and ungrouped, the index cannot go out of bounds, and it cannot land inside a group block. What is missing is routing guidance — nothing says when to reach for this instead of fgui_insert_object or a relation/group tool.

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