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

Goes well beyond the annotations: Google's size/duration/resolution limits (~30s, ~100MB, 720p), server-side download behavior, multi-minute processing latency before the video appears, and the confirm=false preview vs confirm=true publish safety model. This is exactly the operational context annotations like readOnlyHint=false cannot convey.

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?

Front-loaded with the core purpose and sibling differentiation before drilling into hosting, limits, category, safety, and location. Dense em-dash chaining makes it longer than ideal, but every clause earns its place with no 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?

For a 4-parameter destructive-free write with an output schema already defined, the description covers everything an agent needs: hosting requirement, platform constraints, async processing expectations, preview/publish safety, and location resolution. Nothing material is missing.

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 description coverage is 0%, so the description carries the full load, and it largely does: it enumerates the category values (ADDITIONAL default, EXTERIOR, INTERIOR, PRODUCT, AT_WORK, FOOD_AND_DRINK, MENU, TEAM), explains confirm's preview/publish semantics, and documents location's accepted forms. Only video_url format inheritance and location auto-match edge cases are left slightly implicit.

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?

Opens with a specific verb+resource ('Adds a VIDEO to a Google Business Profile') and explicitly distinguishes itself from the sibling gbp_upload_photo by noting this is the video counterpart, which only takes images. An agent can route between the two upload tools without opening either schema.

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?

States the precondition that video_url must be a publicly reachable direct link and gives explicit remediation ('if the file is only on a computer, host it somewhere public first'). It also names the alternative (gbp_upload_photo) for the image case and points to gbp_list_locations as the source of valid location values.

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