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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation profile is covered by structured data. The description adds some helpful behavioral context: the system reconstructs the image, applies gradual 0-100 changes to avoid exaggeration, and preserves identity. It does not, however, disclose the asynchronous task flow (polling) or any side effects; this is moderate added value, and there is no contradiction with annotations.

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 description is front-loaded with the core purpose and mechanism in the first paragraph, which is good. However, the third paragraph contains marketing fluff ('refreshed, confident, and professional appearance') that adds no operational value, and there is some redundancy about natural/balanced outcomes across paragraphs. It earns its first paragraph but could be tightened.

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?

Despite having an output schema, this is a high-complexity tool with four union variants in the request schema (auto/custom × url/id). The description omits critical operational context: the distinction between 'auto' and 'custom' type (and that 'auto' is the misleading default while 'custom' requires non-zero features), the detection flow referenced by 'index' (which relates to a sibling detection tool), and the globals for skin-smooth strength. These gaps would lead an agent to invoke the tool with suboptimal defaults.

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 description coverage is 50% — version, src_file_url, src_file_id, features, and polling are already documented in the schema. The description adds semantic value by explaining that the numeric feature values (0-100) represent a gradual increase in enhancement level, which the schema does not convey. However, it does not clarify the misleading type default ('auto' with default 'custom'), the 'index' detection reference, or the global skin-smooth parameters, so compensation is partial.

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?

The description clearly states the verb and resource: it performs generative facial enhancement/refinement on an image, analyzing facial structure, skin quality, and proportions while preserving identity. It explicitly contrasts with filters, and the named feature areas (eye bags, cheeks, forehead, face shape, mouth) map to what the tool does. It doesn't explicitly differentiate from the closely-related AI-Face-Reshape sibling, so it stops short of 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 gives use-case context ('suitable for social media, profile photos, creative content, or business use') and implies it is for natural, balanced enhancement. However, it does not mention when NOT to use it, nor does it name alternatives such as AI-Face-Reshape or AI-Aging-Simulation that an agent should pick instead. The when-to-use is only implied.

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