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

Annotations already mark this as destructive and non-read-only, and the description adds substantial context beyond them: it deletes the stored file, stages changes on running/paused projects, returns cleared:false as a no-op, and reports staged IDs rather than necessarily the IDs passed in. It also discloses that finished or archived beta project content cannot be edited.

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 core action is front-loaded in the first sentence, followed by behavior that matters for safe invocation: no-op handling, immediate versus staged execution, and archived-project restrictions. The density is justified by the staging complexity, and there is no 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, the description covers the action, side effect on stored files, no-op result, staging lifecycle, related tools, ID behavior, and editability restrictions. An agent has enough information to invoke it correctly and interpret the staged response.

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 100%, so taskId and productId are already documented in the input schema. The description still adds non-obvious meaning by noting that taskId may be either the live or staged ID and that the response returns the staged row with liveVersionId linking back.

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 states a specific verb and resource: it removes media from a task and deletes the stored file. It also distinguishes the operation from setTaskMedia by describing it as equivalent to setTaskMedia with attachmentId=null, so an agent can identify the exact action without opening another 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?

The description explains the no-op case when the task has no media, the immediate-apply case for draft/scheduled projects, and the staged case for running/paused projects. It names the related commitTaskChanges, revertTaskChanges, and getBetaTasks behaviors that determine how staged removals are published or discarded.

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