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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered structurally; the description usefully confirms the list is limited to the connected account. It adds nothing about ordering, list size, or pagination, which matter for a paged listing tool.

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?

Two short sentences, front-loaded with what the tool returns and followed by the downstream action it enables. No filler or redundancy.

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 read tool with no output schema, the definition covers purpose and downstream use but leaves return shape and pagination behavior unstated. Acceptable but not fully self-sufficient for an agent that needs to enumerate a full asset library.

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% and the sole parameter is `page`, yet the description never mentions pagination, page size, or how results are ordered across pages. With only one parameter and a schema-provided default/min/max, the omission is minor but real — an agent gets no hint that this list is paged at all.

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 specific verb and resource ("List photos already uploaded") and scopes it to the connected account, so an agent knows this is an inventory read rather than a generation action. It stops short of naming a sibling, but the follow-up sentence makes the relationship to video generation clear enough to disambiguate from generate_video.

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 phrase "Use an ID from this list to generate a video" implicitly positions this as the prerequisite lookup step before generation, which is genuine usage context. However, it gives no guidance on when not to call it, whether it's exhaustive, or how to page through results when the list is long.

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