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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false, so the description's burden is to add mutating-task context such as unit consumption, polling behavior, or failure modes. It discloses none of that; the only behavioral nugget ('one face at a time') is far more fully specified inside the schema than in the description.

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 lines are tagline copy rather than capability spec, and the closing sentence ("we've got you covered") is pure filler. Nothing about the actual operation is front-loaded, so the reader must get past marketing prose to find the one useful phrase.

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?

This is a high-complexity generative tool: four anyOf input branches, nested face_mapping, a polling default, and unit-consuming failures. The description covers only the surface premise and omits the detection prerequisite, billing/error semantics, and branch selection guidance.

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 reported at 50%, below the threshold where the schema alone suffices, so the description should compensate for the anyOf branches and the src/ref URL-vs-ID choice. It says nothing about any parameter, leaving the polling flag, the four input-branch variants, and the face_mapping structure entirely to 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?

"Lets you rebuild any group photo, one face at a time" does state a verb and resource, and the 'one face at a time' phrase hints at a real constraint. But "Rebuild the faces" and "AI Retake" are close enough to sibling AI-Face-Swap and AI-Retake-Detection that an agent gets no discriminating signal about which of the three to call.

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 only usage framing is marketing audience language ("funny pictures" vs "a professional tool"), which does not tell an agent when to choose this over AI-Face-Swap or the detection sibling. There is no mention of the face-detection prerequisite or the one-task-per-face workflow, both of which gate correct invocation.

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