Recut clip job (spends credits)

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

Annotations declare destructiveHint=true and non-idempotent, and the description goes well beyond them: exact credit cost (1 per started minute, min 1, max 30), that the original job/clips stay unchanged, the 10-minute dedup window, the quote-is-upper-bound nuance for the billed range, and the caching/inheritance behavior. This is the kind of context annotations cannot carry, and it does not contradict the destructive/running-cost annotation.

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?

Four tight paragraphs that front-load purpose, then billing, then prerequisites, then inheritance/alternatives. Every sentence carries substantive information for a 23-parameter credit-spending tool, though it is dense enough that it could be trimmed slightly without loss.

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?

Given the tool's cost and 23 parameters, the description covers billing, prerequisites, state eligibility, inheritance, alternatives, dedup behavior, and the follow-up call. An output schema exists, so return values need not be explained, and nothing an agent needs to invoke it correctly 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%, so the baseline is 3, but the description adds cross-parameter semantics the schema cannot express: default billing of the reused range, that start_sec/end_sec defaulting makes the quote an upper bound, that only passed settings change and everything else is inherited, and the requirement that new_moments=false only works when the range matches the original.

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+resource ('Creates a new clip job from the same source video as an existing job') and immediately enumerates the differentiators (caption style, hook style, clip length, etc.). It cleanly distinguishes itself from create_clip_job (new job) and retry_clip_job (same settings) without needing the schemas.

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?

Explicit prerequisites ('run quote_clip_job... get the user's agreement and pass max_credits'), a clear state restriction ('Works for completed and failed clip jobs, not for jobs that are still running'), an explicit alternative for the same-settings case ('use retry_clip_job'), and a next step ('call get_clip_job with wait_sec=50'). When/when-not and alternatives are all named.

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