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

Beyond the annotations, the description discloses key behavioral traits: the handoff is short-lived, it is not proof of upload completion, and it fails or can be denied. It also states what the operation does not do (does not start generation or modify an existing asset), adding safety context beyond the basic destructiveHint/readOnlyHint flags.

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 long, but nearly every sentence carries operational value: when to use, fallback behavior, local-file guidance, safety cautions, and failure handling. It is front-loaded with the primary use case, though the density of caveats makes it less immediately scannable than it could be with light structuring.

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 single-parameter tool with no output schema, the description is unusually complete. It explains the returned browser destination fallback, the importer and helper flow, what to do after asset IDs are returned, when to call list_media, and how to behave on failure. An agent has enough context to call this tool correctly and respond to outcomes.

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 0%, but there is only one enum parameter. The description reinforces the semantics by naming all supported media kinds (image, video, audio) and framing kind as the requested media type, so an agent can confidently select a value. It could be slightly more explicit about the parameter name, but the meaning is clear from context.

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 uses a specific verb and resource: it creates a short-lived handoff for private image, video, or audio reference media. It also distinguishes itself from related tools by explicitly noting it does not start generation or modify existing assets, so an agent can separate it from list_media and generation-oriented siblings.

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 gives an explicit trigger condition: use it when the host cannot expose a file handle. It also provides concrete guidance for local files in Codex or Claude Code, including creating one link per file and using the packaged helper, plus a clear post-upload workflow with list_media. This is actionable and goes well beyond a generic statement.

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