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

Annotations already declare destructiveHint=true, idempotentHint=true, and closed-world, so the safety bar is lower. The description nonetheless adds genuinely new behavior: scope of destruction ('preserving unrelated material'), a gating requirement ('server-recorded approval'), and a cost side-effect ('within the shared credit ceiling') – all absent 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?

Two sentences, front-loaded with the operation and followed by the precondition, with no filler. The density of internal jargon ('bounded native Film specialist') costs some clarity, but nothing is redundant.

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, and annotations cover safety and idempotency. What is missing is a plain account of what the revision actually changes in the scene versus the clip, and how approval is obtained – non-trivial for a destructive, credit-consuming operation.

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 both parameters (proposal_id, request_key) carry their own descriptions, so the schema already does the heavy lifting. The description adds nothing about how proposal_id relates to the required approval or how request_key drives the idempotent behavior, so it stays at the baseline.

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 verb is 'Run' and the object is 'the approved bounded native Film specialist on the exact scene and clip' – an agent can infer this re-runs scene generation rather than authoring a new scene, but the phrasing is jargon-heavy and never plainly states 'revise/regenerate this scene's media.' It does not name any sibling (e.g., generate_scene_media, update_scene_prompt, native.generate_scene_media) that an agent should consider instead.

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?

One real precondition is given: 'Requires server-recorded approval within the shared credit ceiling,' which tells the agent it cannot call this before approval exists. However, there is no guidance on when to choose this over sibling generation or editing tools, and no statement of when not to use it.

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