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

Goes well beyond the annotations by disclosing the cost model (Horizon Units charged only for those minutes, over-limit refused, refunded on failed jobs), the retry semantics of request_key, and the async pattern (returns job_id, poll job_status, then list_clips). These are non-obvious operational facts an agent cannot infer from readOnlyHint/idempotentHint.

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 use case, then a clearly labeled "Not for:" block and a returns/polling tail, with no filler. Slightly dense in the middle where cost, idempotency, and return flow are packed into semicolon-linked clauses, which makes it harder to scan than it could be.

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 six-parameter job-creating tool whose parameters are entirely undocumented in schema, it covers inputs, cost gate, idempotency, and the follow-up calls needed to retrieve results. The output schema handles return shape, and the description still supplies the job_id to job_status to list_clips path an agent needs.

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 0%, so the description carries the full burden and does so for all six parameters: duration bounds on start/end_seconds, origin of project_id (list_projects), accepted forms and "none" sentinel for clipping_preset, the approval contract for max_hu, and the stable-string rule for request_key.

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?

Names a specific verb and resource (make ONE captioned vertical clip of exactly start_seconds to end_seconds of project_id) and anchors it with concrete user phrasings like "clip 1:02:10 to 1:03:00". Explicitly contrasts with find_clips, find_moments and edit_clip, so it is distinguishable without opening a 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?

Provides both an inclusion rule (user wants one exact stretch, or a match from get_moments) and an explicit "Not for:" exclusion list with the correct alternative for each case. It also supplies the required pre-call workflow: estimate_hu with the same range, show the number, pass the approved amount as max_hu.

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