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

The description adds key behavioral context beyond the annotations: the timing effect ('Applies to posts published or edited after this call'), the lack of retroactive changes, and the propagation behavior ('Every copy of the same file in your workspaces follows'). These traits are not captured in the annotations (readOnlyHint: false, destructiveHint: false) and would otherwise be unknown to the agent, so this is valuable disclosure.

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 description is two sentences with no redundant words. It front-loads the core action, then packs in scope, timing, an alternative tool, and a workspace behavior. Every clause carries information that an agent needs, earning its place without any fluff.

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 simple mutation tool with no output schema, the description covers purpose, behavior, and parameter usage comprehensively. The only missing element is an explicit note about what the tool returns (e.g., success or updated media) or error cases beyond the workspace-id hint. Since there is no output schema, a brief mention of the return value would fully round it out, but the current description is already strong enough for correct invocation in most scenarios.

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?

Even though schema coverage is 100%, the description adds significant meaning to the parameters. It tells the agent where the id comes from (media_presign, media_from_url, or media_upload_status) and gives nuanced guidance on workspaceId: when it's needed, that the error reveals the ids, and to leave it out if already decided without asking again. This goes beyond the schema's basic type descriptions and aids correct invocation.

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 explicitly states the verb ('Mark or unmark'), the resource ('uploaded image or video'), and the attribute ('aiGenerated'). It also distinguishes itself from the sibling update_post by noting that posts already out do not change and referencing update_post for that case, making it easy for an agent to select the right tool.

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 clear when-to-use ('Mark or unmark...') and when-not-to-use ('posts already out do not change') guidance, and explicitly names the alternative (update_post) for already-published posts. It also provides practical instruction for the optional workspaceId parameter, including when to omit it and not to re-ask the user, which is directly actionable.

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