fgui_find_unused

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

No annotations are supplied, so the description carries the full burden, and it delivers: it declares the tool read-only, states the minimum version (0.8.19+), and explains that the judgment is limited to in-project references with runtime URL usage excluded. The one behavioral gap is include_branches, which is not mentioned anywhere, so branch-scoped behavior is invisible.

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?

It is front-loaded with the purpose and read-only/version status, then the interpretation caveat, then parameter notes, so each block serves a purpose. The middle caveat sentence is slightly dense but not padded; the only dead weight is that include_branches never appears despite being in the schema.

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 the description did not need to enumerate return fields, yet listing package/path/URL/size and image dimensions is harmless reinforcement. For a read-only, zero-required-parameter query tool this is nearly complete, with the include_branches parameter the sole unexplained element.

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 four of five parameters: packages (package name or ID, omitted = whole project), types (with the concrete enum values image/font/sound/movieclip/component, which the schema itself lacks), max_items (with the important note that unusedCount remains the true total), and skip_exported. Only include_branches is left 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 gives a specific verb and resource ('找出工程内没有任何引用位置的资源') and sharpens the definition with the 'zero references within the current project' criterion, which is genuinely more precise than the tool name alone. It never mentions related siblings such as fgui_query_references or fgui_find_duplicate, so an agent still has to infer how this differs from reference- or duplicate-analysis tools.

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?

It gives clear situational guidance: exported resources may be loaded at runtime by URL, they are still listed and marked 'exported' by default, and the user should confirm before deleting or modifying. It also states that skip_exported=True excludes them, so the agent knows the safe path. It stops short of naming an explicit alternative tool or a when-not-to-use condition.

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