import_game

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

With no annotations at all, the description carries the full burden and does substantial work: it discloses that 'Files are copied; the game folder is not changed' (non-destructive to source), that 'Existing sections and same-named assets are merged' (idempotent-ish merge semantics rather than overwrite), and that folder access must be pre-granted. Not disclosed are the return shape, whether the import is long-running/async, or what happens on partial failure or name collisions beyond the merge note.

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 action and the source types, and the mid-sentence inventory of imported artifact types earns its place by conveying scope. The final two sentences carry the most decision-relevant facts (copy-not-move, merge behavior, access prerequisite, preview). It is a single dense paragraph, slightly long, but no sentence is filler.

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 three-parameter mutation with no annotations and no output schema, the description covers the important behavioral questions: what gets created, whether the source is modified, merge semantics, and the access prerequisite. The gaps are the undocumented 'project' parameter and the absence of any indication of return values or run duration for what is likely a heavy operation.

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 for all three parameters. It explains preview well ('set preview=true to only list what would be imported') and implies game_path via 'the game folder' and the access-prerequisite sentence, but the 'project' parameter (default 'default') is never mentioned in any form, leaving the target-project semantics 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 opens with a specific verb and resource: 'Import a Godot, Unity or Unreal project (or any folder of game art) into a Glob project', then enumerates the concrete artifacts created (characters, models, animation clips, textures, weapons, kits, skies, design docs). It is clearly distinguishable from workspace_* CRUD tools and generate. It stops short of naming the closest sibling, scan_game_project, so the boundary between importing and scanning is left implicit.

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 real preconditions ('The user must have granted Glob access to the folder (Settings > Storage & access)') and a mode switch ('set preview=true to only list what would be imported'), which is actionable when-to-use guidance. What it does not do is name an alternative tool or state when NOT to use this one, e.g. pointing to scan_game_project for read-only inspection.

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