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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false), but the description adds material context beyond them: the save creates an immutable revision, server-owned timing is preserved, validation occurs before save, and notably no model/queue/provider/credit is consumed. That last fact is genuinely useful for distinguishing this from credit-consuming generation siblings.

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 dense sentences with the action verb front-loaded and no filler. It packs several distinct facts efficiently, though the final sentence is a clipped fragment rather than flowing prose.

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?

An output schema exists, so return values need no explanation. For a non-idempotent write the description covers validation, immutability, timing preservation, and credit neutrality; it omits only the failure mode when expectedRevisionId is stale, which is largely inferable from the 'exact' framing.

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 86%, so the baseline is 3. Most of the description's parameter talk ('one DirectedShot per fixed shot order', 'exact expectedRevisionId/audioAnalysisId') restates schema text. The one addition is that visualWorld, though optional in the schema, is required for quoting — a useful but single new fact.

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 ('validates and saves a finished Music storyboard') and the payload shape (one DirectedShot per fixed shot order). The word 'finished' implicitly distinguishes it from the draft-write sibling studio_storyboard_write, but no sibling is named explicitly, so differentiation is left to inference.

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?

Implies the tool is the finalization step ('finished storyboard', 'exact expectedRevisionId/audioAnalysisId') and states that visualWorld is required for quoting, but never says when to use this versus studio_storyboard_write, studio_storyboard_prepare, or studio_storyboard_approve. Usage context is inferable, not explicit.

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