godot_set_tilemap_cells

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

The annotations only state this is not read-only, not idempotent, and not destructive. The description's 'place or clear' phrasing adds genuine behavioral signal by disclosing dual paint/erase semantics, which helps an agent understand that clearing cells is within scope. However, it stops short of disclosing meaningful in-scope behaviors implicitly enabled by the schema, such as the 'set source_id to -1 to erase' convention or the side effect of clear_before_paint wiping existing cells, so the disclosure feels incomplete for a batch mutation.

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?

A single, grammatical, front-loaded imperative sentence with zero filler words. 'Place or clear' immediately leads, followed by the target resource. Every word carries meaning: 'coordinate grid' disambiguates from world-space positioning, and the dual-verb construction is information-dense without ever being verbose. It is appropriately sized to be read in a single glance.

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 tool with a nested TileCell entity, a batch cells array, and a clear_before_paint flag with significant side effects, a single sentence leaves meaningful gaps. The description never hints at batch semantics, the destructive potential of clear_before_paint, error behaviors, or how this relates to the sibling godot_get_tilemap_cells for verification workflows. An output schema exists, so return values need no explanation, but the operational gaps remain material for correct invocation.

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?

The description, at 'Place or clear tiles on a TileMapLayer coordinate grid', explains none of the tool's parameters—node_path, cells, clear_before_paint, or the nested TileCell fields. With schema description coverage at 0%, the description fails to compensate for the gap; the well-documented inline schema is what keeps this from being a 1. It does indirectly hint at the place-vs-clear distinction reflected in source_id semantics, but that linkage is not drawn for the agent.

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?

'Place or clear tiles on a TileMapLayer coordinate grid' pairs specific verbs ('place or clear') with a clear resource ('tiles on a TileMapLayer coordinate grid'). It implies both paint and erase modes and situates the operation within the Godot tilemap domain, distinguishing it from siblings like godot_get_tilemap_cells and godot_create_tilemap_layer by contrasting set vs. get/create operations, though it never names those siblings explicitly.

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?

No when-to-use guidance is provided. There is no mention of when to reach for this tool instead of godot_get_tilemap_cells, no prerequisite about having an active TileMapLayer node selected, and no note about the schema's batch-oriented design being preferable for multi-cell updates. The only hint of usage is that it involves painting or erasing tiles, which leaves the agent to infer all context from the tool name.

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