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

Goes well beyond the destructiveHint annotation: it states the stored file is deleted, that an empty step returns cleared: false, that changes are staged on live betas until commitTaskChanges, and that finished/archived projects cannot be edited. That is exactly the mutation risk profile an agent needs before calling.

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 destructive action comes first, then edge cases, then the staging contract, then the hard limit. Every sentence carries operational information and none restates the tool name.

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?

With no output schema, the description still tells the agent what a response looks like (cleared: false, staged rows with liveVersionId) and when the call is refused. There is no meaningful gap for a destructive three-parameter mutation.

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 all three ids are documented, but the description adds real meaning: staging accepts both live and staged ids yet always returns the staged row with a liveVersionId back-link, so the agent should expect unfamiliar ids in the response.

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?

Starts with a specific verb and resource ('Removes the media... shown on a step and deletes its stored file') and names the sibling it mirrors (setStepMedia with attachmentId=null), which distinguishes it from removeTaskMedia and getStepMedia.

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?

Explains the no-op case, the draft/scheduled immediate path, the running/paused staging path, and which sibling tools publish or discard staged changes (commitTaskChanges, revertTaskChanges, getBetaTasks). It stops short of explicitly contrasting step-level vs task-level removal with removeTaskMedia, so a 4 rather than 5.

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