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

The annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: the expiration/retention rule that videos are deleted 30 days after creation, plus the set of fields the caller will receive despite there being no output schema.

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?

It is short with no filler, and the core purpose is front-loaded. But the middle clause is an unpunctuated fragment and the raw JSON argument blob appended at the end breaks the flow rather than being integrated into a readable structure.

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?

With no output schema, listing the returned fields and the 30-day deletion rule makes the definition reasonably complete about results. The remaining gap is the nested query object: with 0% schema coverage, the meaning and default behavior of client_id and all_spaces are left unexplained.

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 single parameter is a nested object, so the description bears full responsibility. It restates the argument names and shows an example payload, but never explains what client_id scopes to or what all_spaces=true actually changes, so an agent cannot reason about the values beyond copying the literal example.

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 opens with a specific verb and resource ("List the finished videos of the account") and enumerates the returned fields (job id, title, duration, workspace, expires_at), which clearly distinguishes it from siblings like kelpo_get_job or kelpo_video_download. The trailing clause "the sources of a montage (kelpo_select_editing_sources)" is grammatically fragmentary but does signal the relationship to that sibling.

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?

Referencing kelpo_select_editing_sources implies this tool is the way to discover candidate montage sources, which gives the agent a partial sense of usage. However, there is no explicit when-to-use/when-not guidance versus kelpo_get_job, kelpo_video_download, or kelpo_list_clients, and no stated prerequisites for calling it.

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