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

The annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, but the description adds the crucial behavioral fact that the tool opens nothing and only returns instructions, which is exactly what an agent needs to avoid assuming the resend already happened. The note that no public EZ Lawn Biller API exists explains the browser-automation dependency, though it spends a lot of words on 404 research rather than on runtime behavior like login or selection prerequisites.

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 instructions, opens nothing, then use cotlet_browser_*) is front-loaded, which is good. But the closing sentence about /api, /developers, /docs returning 404 and QuickBooks being the only integration is verbose background that does not help invocation and dilutes the actionable content.

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 output schema, the description correctly describes the return shape (step-by-step screens, buttons, fields). It omits practical prerequisites: whether the user must be logged into the Cloud Browser, what happens if nothing is selected, and how the instruction payload is structured (single blob vs steps), leaving real gaps for a guidance-only tool.

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?

There are zero parameters, so the schema carries no semantics to compensate for; baseline 4 applies. The description does not invent parameters, which is consistent with the empty object schema.

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 does state the resource (EZ Lawn Biller account) and the action (resend selected), and it clarifies that the tool's real output is step-by-step instructions rather than the resend itself. However, it never says what "selected" refers to (invoices, statements, customer emails) and it draws no boundary against near-identical siblings such as ez_lawn_biller_send_resend or ez_lawn_biller_email_selected, so an agent cannot confidently choose among them from this text.

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 useful sequencing guidance: call this for the screens/buttons/fields, then execute with the cotlet_browser_* tools in the Cloud Browser. It never says when to prefer this over the sibling send/resend tools or when this is the wrong choice (e.g., no items selected), so an agent must infer which resend tool to use.

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