katto_adjust_clip

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

Goes well beyond the annotations: discloses the 7-day source retention and the 410 failure mode, that video quota is not consumed, that the original clip is preserved, how captions are sourced for extended parts, the non-idempotent render-per-call behavior, and the full return shape. Consistent with destructiveHint=false and idempotentHint=false rather than contradicting them.

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 action, then constraints, then edge cases, then return shape; nearly every sentence carries decision-relevant information. It is dense and runs long, but there is little that could be cut without losing an operational fact.

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, the description supplies the return fields and points to katto_get_rerender for the resulting clip_url, plus the range/source/quota constraints an agent needs before calling. Nothing material for correct invocation 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 coverage is 100% and the schema already documents each offset's sign meaning, so the baseline is 3. The description adds genuinely new semantics beyond the schema: offsets are relative to the ORIGINAL bounds and 'two calls do not add up', which prevents a real misuse pattern.

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 pair (trim/extend), the exact resource (one finished clip), the mechanism (moving start and/or end) and the consequence (re-render). An agent can tell this apart from katto_rerender_clip or katto_create_clip purely from the description.

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?

Gives concrete conditions: result must be 3-180 s, must stay inside the source video, extending only works while Katto keeps the source for 7 days, and otherwise trimming still applies (410). It does not explicitly name the sibling (katto_rerender_clip) as the alternative for a different use case, which keeps it short of a 5.

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