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

Adds substantial context beyond annotations: bytes are measured, one canonical revision is created, stricter model limits or unsupported inputs refuse before payment, clips stay as video references rather than sampled pictures, empty input clears, and identical retries reconcile the same write (consistent with idempotentHint). This is exactly the kind of mutation/payment/idempotency detail annotations cannot convey.

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-loads the core action and scope, then layers constraints and edge cases in dense but purposeful sentences with no filler. Slightly jargon-heavy ('Stricter model limits or unsupported driving-video inputs') but each sentence carries distinct information.

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 an output schema present, return values need no explanation, and the description covers the mutation semantics, payment gating, idempotency, and clearing behavior for a 6-required-param tool. Reasonably complete, though the rightsConfirmed precondition and the relationship to the read sibling are left implicit.

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 67% and the description meaningfully enriches the key parameter: 'up to three' matches maxItems, clips must be 1–15 second owned uploads, and empty attachmentIds is a clear/clearing sentinel. It does not, however, clarify rightsConfirmed (const true) or the expectedRevisionId concurrency guard beyond implying reconciliation.

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 (binds) with a precisely scoped resource (up to three owned uploaded 1–15s original clips as shot motion/composition references) and a concrete side effect (creates one canonical revision). An agent can tell this apart from the read sibling (studio_shot_video_references_read) 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?

Provides an implicit usage rule ('Empty attachmentIds clears the selection') and a refusal condition (unsupported driving-video inputs refuse before payment), which hints at preconditions. However, it never explicitly names the read counterpart or states when to prefer this over other shot/storyboard write tools, so usage routing remains inferred.

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