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

Goes well beyond the annotations: it discloses the 20-look / 50-filter caps, that saving under an existing name replaces it, that only recreatable settings are kept while masked/disabled/foreign filters are skipped and reported, that apply takes a checkpoint and rolls back on refusal, and that nothing-to-save is an error. This is the kind of operational detail an agent must have before mutating a user's photo.

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 opening sentence front-loads purpose and the rest is organized op-by-op with consistent op=... labels, so it is navigable despite being a single dense paragraph. A tight per-op bulleted layout would scan faster, but no sentence is filler.

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 carries the return-shape burden and does so: list returns step counts and save times, unreadable looks are reported rather than used, and skipped filters are listed in the save result. Error, limit, and rollback behavior are all covered, leaving nothing an agent needs before calling.

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%, so the baseline is 3, but the description adds real meaning the schema lacks: which params each op requires, that layer is required only for multi-layer images, that layer_id takes priority, and that replace forces an earlier apply to be removed first. That is more than restating 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 resource ("Your saved looks: filter recipes kept on this server, for you only") with a clear scope and ownership qualifier, and the sub-operations are enumerated explicitly. It is clear what the tool manages, but it never differentiates itself from the sibling apply_look, which an agent could reasonably confuse with op=apply here.

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?

Each op is given explicit when/why guidance: save reads live filters from a layer and requires a named layer when multi-layer, apply puts a look back on a layer with replace semantics, list is for enumeration, delete removes the definition but leaves already-added filters on the photo. It also names the prerequisite sibling (manage_filters op=list) and covers the batch-invocation case.

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