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

Annotations already carry the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), so the description's lower burden is satisfied in part by the precedence/fallback explanation, which is real behavioral context. It does not disclose what clear_model_default actually removes, whether the prior default is recoverable, or whether the change is account-wide. With annotations covering the mutation profile, this is adequate but not rich.

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?

Three short sentences with no padding, and the parameter conditionals are grouped at the end. But the first sentence is a fragment that never anchors the action, so the opening does not front-load what the tool does — the most important information is implicit throughout.

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 annotations present, 100% schema coverage, and no output schema, the description needs to supply the operative action and any permission or scope constraints. It supplies the fallback semantics well, but omits that this mutates account-wide defaults, what clear_model_default destroys, and whether elevated permissions are required — meaningful gaps for a destructive, non-idempotent tool.

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 the baseline is 3 and the schema already documents every parameter's role, including the provider and talking_head conditionals. The description's restatement of "voice_block needs provider and segment_video needs talking_head" largely duplicates the schema, adding no syntax, format, or validity detail beyond it.

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 is a verbless noun phrase — "The account's default model and settings for one kind of generation" — that names the subject matter but never states what the tool does. An agent cannot tell from the text alone that this sets or clears an account-level default; that must be inferred from the tool name and the action enum. It does gesture at the account-scoped domain, which distinguishes it somewhat from sibling *_edit tools, but the core action is absent.

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?

"Used when neither the call nor the item's prompt editor names one" is a genuine precedence rule telling the agent when an account default is the operative value. "voice_block needs provider and segment_video needs talking_head" gives per-family parameter conditions. However, there is no guidance on when to call account_edit versus siblings like style_edit, voiceover_edit, or editor_edit, and no stated prerequisites.

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