fgui_set_list_items

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

With no annotations present, the description carries the full burden and does so: it discloses that all input is validated before any mutation, that the operation does not enter the Agent undo stack, that changes are unsaved by default, and that unsaved state can be discarded or committed with save (which saves the whole document). It even distinguishes rollback semantics — native-app failures attempt restore and report rolledBack, while save/verify failures do not auto-rollback.

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 action, then semicolon-delimited clauses for limits, validation, rollback and persistence. Every clause carries information, but the telegraphic style and lack of visual grouping make the persistence/rollback section harder to parse than it needs to be.

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 (including rolledBack) need not be spelled out, and the description covers the mutation, validation, persistence and failure paths that an agent must know before calling this destructive-feeling bulk write. The one real omission is how the target List is identified among object_id / object_name / object_path.

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 covers the hard parts: items order equals item order, [] clears, max 1000 entries, supported fields url/title/icon/name/selectedTitle/selectedIcon, omitted fields are cleared, omitted default_item preserves the default component while an empty string clears it, and empty/omitted urls inherit the final default component. However, object_id / object_name / object_path (3 of 8 params) are given no explanation at all, so target resolution is left to inference.

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?

Opens with a specific verb+resource: batch-replace the items of an existing List, and notes the 0.8.26+ version gate. It is clearly distinguishable from the read-side siblings fgui_list_items / fgui_get_list_items and from fgui_set_list_layout, which handles layout rather than content.

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?

States explicit preconditions and exclusions: only unlocked Lists under the current root component, and the user must exit the timeline and group editing first. Also conditions external_reload on save=True plus verify=True. It never names an alternative tool (e.g. insert_list or get_list_items for inspection), so it stops short of a full when-to-use-this-vs-that rubric.

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