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

Annotations only say destructiveHint=true and readOnly=false; the description goes well past that by disclosing exactly what survives (library files persist), what alsoDelete actually destroys (files used by no other project land in Recently deleted), and a 30-day undo window. It also scopes the operation to the current project, which is the risk-relevant nuance for a destructive tool.

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?

Dense but front-loaded: the primary effect comes first, then the library side effect, then the optional flag, then recovery. Parentheticals ('delete_asset deletes one from there', 'a file uploaded by mistake') each carry real disambiguation value rather than 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 destructive mutation with no output schema, this covers return-path behavior (undo, 30 days, Recently deleted) better than most definitions. Remaining gaps are the mediaId-versus-mediaIds choice and what happens if a media item is missing or the project ID is stale, but nothing essential to calling it safely is absent.

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 50% and the description fully compensates for alsoDelete, explaining the cross-project usage condition that the schema's one-liner omits. It adds nothing about why both mediaId (string) and mediaIds (array) exist or which to prefer, leaving that ambiguity unaddressed.

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?

States a specific verb and resource plus the crucial scope boundary: 'takes media items and all their clips out of this project' while 'the files stay in the workspace's library.' It also distinguishes itself from delete_asset and restore_asset by name, so an agent can tell the three apart without opening any 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?

Explicitly routes the agent: use delete_asset to remove a file from the library, use remove_media to detach items from a project, use undo or restore_asset to recover. The conditional for alsoDelete ('a file uploaded by mistake') tells the agent when to pass the flag versus when not to.

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