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

With no annotations, the description carries the full behavioral burden and does well: it discloses sort order (newest decision first), granularity (one entry per video per tab), pagination, that it is free, and specific error behavior (422 for bad kind/run_id/cursor). It stops short of stating auth requirements or rate limits.

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?

Information is front-loaded with the resource and origin first, then scope, paging, return shape, cost and errors. It is dense and slightly run-on ('one entry a video on each tab across all runs'), but no sentence is wasted.

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 paginated list tool with an output schema, the description covers filtering, ordering, paging, return shape and errors, which is nearly everything an agent needs. Only auth context is absent, and the return values are already backed by the output schema.

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 only 40%, and the description compensates by clarifying limit bounds and default, the run_id scoping meaning, the kind choice, and the cursor via the next_cursor return. It adds real meaning beyond the sparse schema, though api_key is left unexplained.

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 resource ('the videos you kept with keep_find') and explicitly ties it to the sibling action that produced the data, plus a scope note about long-form hooks and packages. It does not explicitly distinguish itself from the sibling list_keeps, so it falls short of a 5, but an agent can tell what it lists.

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?

It describes the two retrieval modes (all runs vs. one run_id) and mentions the kind filter, which implies when to use it. However, it never names an alternative such as list_keeps or list_finds and gives no when-not guidance, leaving routing between the sibling list tools to inference.

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