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

The description adds meaningful behavioral context beyond the annotations: it explains that `learn` shows visitors nothing, that `act` acts in the user's name, and that `shadow` only proposes changes without showing them. It also discloses the activation permission requirement. This complements the annotations rather than contradicting them, though it does not go into reversibility or failure behavior.

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 three sentences with no filler. It front-loads the main action, defines both mode axes compactly, and ends with the permission requirement. Every sentence earns its place, and the density is appropriate for the complexity of the tool.

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?

Given the tool's three optional parameters, full schema coverage, annotations, and an output schema, the description is nearly complete. It communicates the core operational states, the separate customization axis, and a required permission. It could be more explicit about how to verify or obtain the activation permission, but the essential invocation context is present.

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 schema already documents all three parameters thoroughly. The description largely restates the mode enum meanings and introduces the "separate axis" framing, which helps conceptual understanding. However, it adds little about `siteId` or parameter-specific behavior beyond what the schema provides.

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 action, "Switch the agent on," and immediately defines what each mode does: `learn` watches without showing visitors anything, while `act` lets the agent intervene. It also introduces `customizeMode` as a separate axis with three clear values. This makes the tool's purpose and scope easy to distinguish from sibling configuration tools like cromanion_set_brand or cromanion_set_voice.

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 description gives a useful prerequisite, "Needs the activation permission," which tells the agent an important precondition. However, it does not explicitly name alternatives or say when not to use this tool versus a sibling such as cromanion_grants or cromanion_config. The usage context is implied by the mode definitions, but explicit routing guidance is missing.

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