modify_assets

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

Annotations already carry destructiveHint=true and readOnlyHint=false, so the mutation safety profile is covered and the bar is lower. The description adds that mutation is limited to scalar fields and data.* array paths, which clarifies scope, but it discloses nothing about partial-failure behavior, whether edits apply atomically, or side effects on references to the asset.

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?

Three short sentences, each earning its place: purpose, array-op capability, and exclusions. The primary scope is front-loaded and there is zero 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?

The tool is high-complexity (five operation variants, nested edits array, no output schema), and no schema documentation compensates. The description leaves an agent guessing about op semantics, path conventions, required fields per op, and what the tool returns, so it is not complete enough to invoke correctly on the first attempt.

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%, and the schema's single parameter is a polymorphic array with five op variants (set, unset, insert, remove, move) whose path/value/index/to semantics are entirely undocumented in the schema. The description only lists some valid fields (name, tags, preload) and notes data.* for arrays; it never explains what the ops do or what path means, so it only partially compensates for the coverage gap.

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 ('Edit asset') and enumerates the editable fields: name, tags, preload, and data paths. It also carves out what it does not cover (anim state graph structure, animation events), distinguishing it from modify_anim_state_graph and modify_animation_events. This is specific enough to differentiate it from the many asset-related siblings.

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?

The final sentence gives an explicit when-not: anim state graph structure and animation events are out of scope and require their dedicated mutation tools. However, it never states a positive usage rule or contrasts with other asset-mutation siblings like move_assets or set_asset_text; the when-to-use is only implied by the listed editable fields.

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