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

Annotations declare a non-read-only, non-destructive, non-idempotent, closed-world mutation. The description goes beyond that by disclosing the exact side-effect boundary (no media generation, no credit charge, no library change), the returned artifacts (new brief and quote) and the follow-up requirement to read recipe_key. That is meaningful added context annotations do not carry.

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 removal action and its dependent steps are front-loaded, followed by prerequisites, side effects and follow-up. Sentences are dense and purposeful. The line about photo format being shared across the shoot is somewhat tangentially placed and only loosely tied to the removal action.

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 6-parameter mutation with no output schema, the description covers prerequisites, side-effect boundaries, and the need to read the returned recipe_key before the next edit. Gaps remain on how shot_index is interpreted and on what the returned quote contains, but the core invocation contract is 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?

With 50% schema coverage, the description compensates by explaining that the recipe_key names the brief flow, that look_keys defaults to all looks using that flow while other looks retain theirs, and that the current brief revision is required. shot_index and board_id are only weakly conveyed, so it is not complete, but it adds real meaning beyond the schema.

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 and resource: removes one base shot plus its dependent steps, and notes it revises selected looks via a named brief flow. It is clear about what is removed and what side product (new brief and quote) results. It does not explicitly distinguish itself from the close sibling remove_shoot_step, so an agent must infer the difference from name alone.

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?

Prerequisites are stated well (requires the current brief revision, read returned recipe_key before next edit), which effectively tells the agent when it is safe to invoke. However, there is no explicit routing against alternatives such as remove_shoot_step versus remove_shoot_image, leaving the agent to infer which removal tool applies.

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