create_media_asset

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

Discloses that the tool is deprecated and will fail, and explains the reason (multipart upload init requirement). It also notes it registers a record only and does not upload bytes, and that it returns a signed URL (though the failure statement makes this slightly confusing). This goes beyond annotations (readOnlyHint false, destructiveHint false) by explaining the failure mode and the historical behavior.

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 compact and front-loaded with the primary purpose, followed by the critical deprecation warning and alternative. It includes a targeted hint for `workspace_id` and mentions the return value. While it contains several sentences, each earns its place, and the structure is logical.

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 deprecated tool, the description is quite complete: it tells the agent the call will fail, why, and what to use instead. It also provides a hint for one parameter and mentions the return. Given the tool is deprecated, the description fully serves its purpose of steering agents away, even though it does not detail all parameters. The presence of an output schema is false, but the description covers the essential behavioral context.

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?

The schema has 0% description coverage, so the description must compensate. It explains `workspace_id` with a hint to `list_workspaces()`, but does not describe `hub_profile_id`, `name`, `duration_in_seconds`, or `memory_size_in_bytes`. Since it is a deprecated tool, the lack of full parameter explanations is somewhat mitigated, but the description still only partially compensates for the missing schema semantics.

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 clear verb and resource: 'Create a media (video) asset record in a hub profile.' It also explicitly differentiates from the alternative `upload_asset` by noting the deprecated behavior and pointing to the one-step tool. The purpose is unambiguous and distinct from sibling asset creation tools.

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 provides when-not-to-use guidance: 'DEPRECATED: registers a record only and does not upload bytes; the current backend requires a multipart upload init, so this call fails.' It names the alternative `upload_asset` and directs agents to use it instead. This is exactly the kind of routing an agent needs.

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