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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, but the description adds substantive mutation semantics the annotations cannot express: deleting a bin removes only the shell while keeping contents, moves are atomic and preserve selected subtrees, and dissolve promotes contents to the nearest surviving parent. It also confirms source media is never modified, which is the key safety question for an organizing tool. It stops short of covering failure modes (name collisions, invalid paths) or idempotency caveats, keeping it at a 4.

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?

The scope statement is front-loaded before the operation list and the exclusions, so an agent gets the gist in the first sentence. Five sentences for eight supported actions is efficient, though the middle sentences are dense run-ons that pack several distinct rules together and could be split for readability.

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 10-parameter, non-read-only tool with no output schema, the description covers scope, action routing, destructive semantics, and root defaults — everything needed to pick the right action and parameters safely. What is missing is any hint about what the list action returns (folder IDs, tree shape) or how errors such as an existing folder name are surfaced.

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 coverage is 90%, so the baseline would be 3, but the description adds cross-parameter meaning the schema does not: that folderIds and/or assetIds combine in a single atomic move_entries call, that dissolve_folder accepts folderPath or folderIds, and that Master is the root for the defaulted parentPath/targetPath. This clarifies how parameters interact per action rather than just restating field descriptions.

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 ("Organize the media pool library using user-managed folders") and then enumerates the concrete operations — list, create bins, rename bins, move assets, remove bin shells, rename assets — which map directly onto the action enum. It also stakes out a clear boundary against neighboring concerns ("does not edit the timeline and it does not change source media content"), so an agent can distinguish it from browse_assets, browse_library, edit_item, and manage_timelines without opening the schema.

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 explicit when-to-use framing ("Finder/NLE-style organization only") and explicit when-not exclusions (timeline editing, source media changes), plus in-tool routing between move_entries and dissolve_folder with the exact parameters each takes. The only gap is that it does not name a sibling tool as the alternative for the listing/read side, but the selection guidance among its own actions is clearer than most multi-action tools.

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