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

Annotations already establish readOnlyHint/idempotent/non-destructive, and the description reinforces that with 'opens nothing by itself', which is the single most important behavioral fact here. It also discloses the return content (ordered screens, buttons, fields) rather than only a status. It does not describe response size, formatting, or failure behavior, so it is strong but not exhaustive.

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 key fact (returns steps, performs nothing) is front-loaded in the first two sentences, with the API note last as supporting context. The API paragraph is somewhat long, listing specific 404 paths and a date, but it is evidence rather than filler. Slightly tighter wording would push this to a 5.

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 input schema, no output schema, and only annotations for safety, the description carries the burden and does explain what comes back and what the agent should do next. It is adequate for an instructional tool. The one gap is that it never says what a 'manual adjustment' covers, so the agent cannot confirm the tool fits an arbitrary adjustment request.

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 zero parameters, so there is no parameter-level ambiguity for the description to resolve and the baseline of 4 applies. Nothing in the text misdescribes inputs, and the absence of a required 'adjustment type' argument is consistent with a purely instructional tool.

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 the resource ('Manual adjustment in the user's own EZ Lawn Biller account') and makes clear the tool does not perform the action: it 'Returns how to do it... step by step (screens, buttons, fields)'. This separates it from the actual mutation/browser tools. It stops short of 5 because 'manual adjustment' is never narrowed to the specific kind of adjustment, so the agent still has to infer scope.

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 gives clear context for use: call it to get step-by-step instructions, then 'do it with the cotlet_browser_* tools in the user's EZ Lawn Biller Cloud Browser'. The API research note ('No publicly documented EZ Lawn Biller API') supports why this path exists. No explicit exclusion versus other how-to style siblings is stated, keeping it at 4 rather than 5.

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