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

With readOnlyHint=false and destructiveHint=false, the agent is left guessing about side effects, and the description fills that gap by declaring no media generation, no credit charge and no library change. It also names the return artifacts (new brief and quote) and the optimistic revision requirement, which explains the non-idempotent behavior.

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?

The operation and its constraints are front-loaded in the first two sentences, followed by effect disclosure and return behavior, with no filler. A couple of phrases such as "Photo format is shared across the shoot" are compressed to the point of being cryptic without prior context.

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 an 8-parameter planning mutation with no output schema, the description covers preconditions, defaults, side-effect boundaries and what is returned. It leaves some parameters (brief_id, shot_index) undocumented, but the critical workflow facts an agent needs to call it safely are present.

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?

At 50% schema coverage the description must carry weight, and it explains the trickiest interactions: the named flow (recipe_key), the affected looks with an all-looks default, and the append-vs-replace split that maps to step_index. brief_id, shot_index and expected_brief_revision semantics are only loosely implied rather than spelled out.

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 pair ("Append or replace") and a precise resource ("one prompt-based image edit"), scoped to a shot/look within a brief flow. That qualifier distinguishes it from siblings like plan_shoot_image, plan_shoot_background_removal or plan_shoot_upscale, though no sibling is named 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?

Gives real preconditions and sequencing: it requires the current brief revision, defaults to all looks on the flow, and instructs reading the returned recipe_key before the next edit. It does not state when to prefer this over the other plan_shoot_* edit tools, so it stops short of explicit alternatives.

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