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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description goes well beyond them: it specifies that all pictures registered against the check are deleted, that covered models cannot render the person until a new check passes, that already-produced videos survive, and that deleting the character withdraws every check. That is exactly the blast-radius and irreversibility context an agent needs before invoking a destructive call.

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 action is front-loaded and no sentence is filler, but the structure breaks down where two clauses run together without punctuation ("the model stops showing them Their checked face is deleted with every picture registered against it"), forcing the agent to re-parse the sentence. A short factual list of what is deleted versus preserved would read far cleaner.

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?

For a two-parameter destructive tool with no output schema, the description covers the essentials: what is destroyed, what is retained, and how the character-level delete interacts. Only the confirmation of a return value or partial-failure behavior is missing, which is minor here.

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 100%, so both parameters are already documented, including the identical "left out, every face check of this person" note on `model`. The description adds only the character-level cascade ("Deleting the character withdraws every check"), so it sits at the baseline for a fully documented 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?

The description opens with a concrete verb+resource: "Deletes the person's checked face," so an agent knows exactly which object is being removed, and the cascade sentences clarify scope (per-model vs. all checks). It does not name sibling tools like get_face_check or start_face_check to sharpen differentiation, which keeps it just 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?

Usage is only implied from the destructive effect — an agent can infer this is the undo path for a face check, but the description never states when to call it versus inspecting state first with get_face_check or how it relates to start_face_check. The `model` scoping note (omitted = every check) gives partial operational guidance but no explicit when/when-not framing.

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