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

Annotations only indicate non-read-only and non-destructive. The description goes far beyond: it explains authority and billing for tools, read-only restrictions for visitors on public personas, forced model behavior with loud refusal rather than silent downgrade, and prerequisites. This is exactly the kind of behavioral context an agent needs and the annotations do not supply.

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 long but every clause carries operational detail—mode behavior, authority, billing, public/private semantics, locked model handling, and prerequisites. It is front-loaded with the core toggle and then systematically expands, so the length is justified and nothing is redundant.

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 tool with no output schema and nested parameters, the description covers the key decisions: what agent_mode changes, how agent_public affects visibility, what locked model behavior is, and the auth/claimed-page prerequisites. It does not mention return values or generic error handling, but the operational context is sufficiently complete for correct invocation.

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%, and the schema descriptions are already rich. The description adds further meaning about runtime implications—e.g., that agent_config.locked forces the model on every runner and that agent_public exposes the persona to any logged-in caller. This goes meaningfully beyond the schema, earning a 4.

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 specific verb and resource: 'Toggle the CALLER's account into (or out of) SUB-AGENT mode (Agent Creation B0).' It names the concrete effects and distinct endpoints, making the tool's function unambiguous and clearly differentiated from any sibling tool that manages accounts or pages.

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?

While it does not explicitly name alternative tools or state when-not-to-use, it gives strong contextual signals: it requires a claimed page and an Authorization header, and it describes the exact behavioral switch. This is enough for an agent to infer when to use it, though explicit exclusions would have made it stronger.

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