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

Beyond the destructiveHint/idempotentHint annotations, the description discloses what is destroyed (the single included revision), that outcomes are irreversible, that human confirmation is required, and the connection-level visibility rule ('Connections see only their own live or owner-test plans'). That is real behavioral context an agent cannot infer from structured fields.

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?

Five short sentences, front-loaded with the irreversible-consumption warning, then the confirmation rule, then the editable surface, then the identifier format. No filler and no repetition of the title.

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 destructive, nested-schema tool whose return values are covered by an output schema, it covers the essentials: cost, confirm-first protocol, ID resolution, and visibility scope. The gap is the relationship between the free-text `request` and the typed `structuredChanges`/`constraintUpdates` fields, and the enum options for framing and audio.

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 description coverage is only 13%, so the description has to carry the load; it does well for taskId (full ID from shoot_plan_list, not planId, eight-char prefix or orderReference accepted) and for constraintUpdates/structuredChanges. However, the required free-text `request`, the required `idempotencyKey`, `replacementBeats`, and the meaning of the framingMode/audioPriority enums are not explained anywhere.

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?

The opening sentence states a specific verb and resource ('Use the plan's one included revision') and immediately frames it as a consuming, one-shot action. It is clearly distinguishable from the sibling shoot_plan_revision_preview, which it names explicitly.

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?

It gives an explicit prerequisite workflow: call shoot_plan_revision_preview first, then confirm with the person. It also states the exclusion condition implicitly by routing preview-style calls elsewhere, and explains the cost of misuse (the revision is consumed and cannot be undone).

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