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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description reinforces and extends this with the concrete claim that it "opens nothing by itself," so an agent knows no state change occurs. It also explains the API gating context, which is real behavioral background not captured by annotations. It stops short of describing output format details beyond the parenthetical "screens, buttons, fields."

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 core two clauses are front-loaded and efficient, but roughly half the text is a tangent about AutoLeap's gated REST Partner API and plan eligibility, which is background justification rather than call-time instruction. That detail is informative but does not help an agent invoke this specific 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?

With no parameters and no output schema, the description carries the burden of explaining the return value, and it does so at a high level (step-by-step screens, buttons, fields) plus the follow-on action. An agent has enough to call it correctly and know what to do next; only the precise response shape remains unspecified.

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?

The schema has zero properties, so there is nothing for the description to disambiguate; baseline for a no-parameter tool applies. The description implicitly justifies the absence of inputs by explaining that details are gathered and acted on via the browser tools, though it never says which customer identity or message is assumed.

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 states a specific verb and resource ("Text a customer") and immediately clarifies that the tool returns step-by-step instructions rather than performing the text itself, which resolves the mismatch between the name and the actual behavior. It also points to the cotlet_browser_* tools as the executors, giving an agent a clear mental model of what this call produces.

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?

It explicitly frames the call as a first step ("Returns how to do it ... then do it with the cotlet_browser_* tools"), which is genuine when-to-use guidance and names the follow-on alternative. It does not distinguish this from the other autoleap_* task tools (e.g. autoleap_send_estimate), leaving the choice among scripting tools to inference.

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