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

Annotations already cover the safety profile (destructive=false, idempotent=false). The description adds genuinely useful behavior beyond that: it discloses the return shape (rc_* item ids) and an undo path ("removable with the department removers"), plus a once-per-short guard. No contradiction with annotations, but disclosure of failure modes is thin.

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?

It is a single compact paragraph with the scoping constraint front-loaded, so nothing is wildly over-long. But the density of idiomatic terms ("short", "cut", "department removers", "B&W only as a device") makes each sentence costly to parse, hurting the front-loading goal.

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?

There is no output schema, and the description does state the return (rc_* item ids) and the undo mechanism, so an agent has the essentials. It is nonetheless incomplete on the operational meaning of the arguments and on how it relates to other apply_* tools, leaving real gaps.

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 33%, so the description must carry weight, and it partially does: it explains name as coming from suggest_recipes, at as "the spoken moment nearest at", and project_id as an explicit immutable scope. It still leaves the enum values and the exact semantics of "nearest at" to inference.

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?

"Write ONE recipe from suggest_recipes" gives a specific verb+resource and names the source sibling, so the core action is inferable. However, the operation is wrapped in opaque jargon ("solved on this cut", "B&W only as a device") and never distinguishes itself from close siblings like apply_look or apply_edit_batch. Purpose is decipherable but not cleanly stated.

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?

Provides real usage constraints — "Once per short" and "flash-safe unless the user asked for flashing" — which imply when the tool is appropriate. But it gives no guidance on when to prefer this over alternatives such as apply_look, and no prerequisites beyond the project scoping statement.

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