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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description reinforces this by saying it 'opens nothing by itself' — an important, non-obvious guarantee that the call has no side effects. It also discloses the return shape (screens, buttons, fields) which the annotations cannot convey. Additional context on permissions or freshness of the steps is absent.

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 action and the no-side-effects guarantee are front-loaded in the first two sentences, which is the right ordering for an agent scanning for behavior. The trailing paragraph on API research (404s at specific endpoints, a dated audit, QuickBooks as the only integration) is legitimate justification for why the browser tools are required, but the endpoint-by-endpoint detail is heavier than needed.

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 zero parameters, no output schema, and full annotation coverage, the description carries the remaining burden well: it states the return content and the fact that the tool is documentation-only. The only shortfall is that it does not describe the step-by-step output's format or whether subsequent steps reference tool names, which an agent following the procedure would want.

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 tool takes no parameters, so there is nothing for the description to disambiguate and the baseline is met. The description correctly implies no inputs are needed to get the instructions. No parameter-level gaps exist.

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 names a specific resource (impersonation state in the user's own EZ Lawn Biller account) and clarifies the tool returns step-by-step instructions rather than performing the change. The distinction between documenting versus executing is stated explicitly, which keeps an agent from misreading the imperative title. It stops short of naming a same-server sibling it must not be confused with.

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 tells the agent what to do next — perform the change with cotlet_browser_* tools in the user's Cloud Browser — which is useful routing. But it gives no explicit trigger condition or exclusion, and never says when a different ez_lawn_biller_* tool would be the right pick. Usage is implied by the impersonation scenario, not stated.

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