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

Annotations already declare the mutation profile (readOnly=false, destructive=false, idempotent=false), and the description adds real value on top: what is NOT affected (no media generation, credit charge, or library change), what is returned (new brief and quote, implying revisioned rather than in-place destruction), and the revision precondition. It does not explain the concurrency failure mode when expected_brief_revision is stale, which keeps it below a 5.

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, front-loaded with the action and its immediate consequence. Every sentence carries information, though the parenthetical "(default: all its looks)" and the trailing procedural instruction make it slightly telegraphic rather than cleanly structured.

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?

With no output schema, the description correctly discloses the return value (a new brief and quote) and the recipe_key to reuse. It also covers the cost/side-effect surface. The remaining gap is the undescribed index parameters and the failure behavior on a stale revision.

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 only 43% and three of seven parameters (shot_index, step_index, expected_brief_revision, brief_id) have no field descriptions. The description compensates for look_keys scoping/default, recipe_key, and the revision requirement, but adds nothing about what shot_index vs step_index identify, so it is partially but not fully compensating.

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?

"Remove one dependent step and reconnect its successor" gives a specific verb, resource, and side effect, which separates it from siblings like remove_shoot_image or modify_shoot_board. It stops short of explicitly naming a sibling or contrasting when to use those instead, so a 4 rather than a 5.

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?

The description supplies the operating context (brief flow scoping, default to all looks using that flow, requirement of the current brief revision) but never states when to choose this over the other board/edit siblings. The sequencing hint "Read the returned recipe_key before the next edit" is the closest thing to explicit guidance.

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