upload_media

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

Annotations already state readOnlyHint=false and destructiveHint=false, so the tool is known to perform a write/upload action without being destructive. The description adds useful behavioral context about accepted input methods (file_path OR media_base64), required filename when using base64, and size/format limitations, which helps the agent avoid failed calls. It doesn't disclose potential side effects or auth requirements, but for a media upload tool this is sufficient.

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, front-loaded with the most critical constraints (formats and sizes), and every sentence earns its place. It gives the two upload modes, a clear output ('media hash'), and usage direction to downstream tools without any 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?

An output schema exists and provides a return-value structure, so the description need not repeat it. The main missing piece is documentation of the ad_id parameter, which the description ignores. Also, there's no mention of whether the ad_id is required for updating existing media. Given the overall detail and the presence of an output schema, the description is mostly complete but has one notable gap.

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 describes all four parameters but provides only names and nullability, with 0% coverage on meanings. The description steps in and clarifies that file_path and media_base64 are alternative sources ('Pass a local file_path OR media_base64 (+ filename)'), and that filename is required with base64. It does not explain the ad_id parameter, but the description still compensates meaningfully for the schema's lack of documentation.

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 clear verb ('Upload'), the resource ('photo' or 'video'), and specifies the exact supported formats and size/size constraints. It also explains the return value is a media hash that feeds into other ad-related tools, distinguishing it clearly from siblings like preview_ad or manage_event.

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 when to use the tool (uploading media for ads) and even gives a pointer to how the result should be used in create_ad/edit_ad. It does not explicitly list exclusions or alternatives, but the sibling context makes this tool uniquely responsible for media upload, and the 'feed into' wording implies the subsequent workflow.

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