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

With no annotations, the description carries the full burden and does well: it explains what each mode actually permits (supervised blocks commands/file edits but keeps connected tools working; edits prompts before each command; full runs without asking) and discloses an important failure mode — escalation is refused when called from inside Caddie's agent turn. It does not say whether the new level takes effect immediately for a running agent, nor what permissions the caller needs.

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 escalation policy is front-loaded and the mode definitions precede the constraints, which is the right order. The sentence is dense with nested parentheticals and quoted values, making it slightly hard to scan, but nearly every clause carries decision-relevant information.

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 mutation with no annotations and no output schema, the description covers the core behavior, the policy constraint, and the refusal path — enough to call it correctly. It omits what the call returns and whether the change affects an already-running agent session.

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 0% and neither property has a description, so the description must compensate — and it does for 'access' by defining all three enum values in operational terms rather than just naming them. The 'agent' parameter is never explained (id vs. name, format, how to discover it), which is the remaining gap.

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?

States the specific verb and resource (change an agent's access level) and immediately enumerates the three access modes with their distinct semantics, so the agent knows exactly what the tool manipulates. It is clearly distinguishable from siblings like update_agent or organize_agents, which do not govern execution permissions.

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?

Gives explicit when-to-use and when-not-to-use rules: lowering access always works, raising requires an explicit user request, and escalation is refused from an agent's own turn — in which case the user must be directed to the Agents page. Nothing about the call/no-call decision is left to inference.

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