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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety bar is low; the description nonetheless adds the key non-obvious trait that this call itself performs no action and no browser session is opened. It also discloses the account scoping ('the user's own SingleOps account'), which matters for multi-tenant correctness. It does not say what the returned steps look like beyond '(screens, buttons, fields)' or whether results are cached, keeping it below a 5.

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 workflow is front-loaded and tight, but the final quoted passage about SingleOps' Lead Entry API ('It is not a general-purpose job-creation or read/write API, and there is no native Zapier integration') is tangential to listing unpaid invoices and pads the definition. Removing that sentence would lose nothing an agent needs in order to call this 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 output schema, the description carries the burden of explaining the return value, and it does: step-by-step instructions covering screens, buttons, and fields, plus the explicit statement that nothing is opened. Together with the follow-on browser-tool handoff, an agent has enough to call this correctly. The one gap is that the concrete shape of the returned instructions (free text vs. structured steps) is left 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 tool takes zero parameters and the schema is fully closed (additionalProperties: false), so there is nothing for the description to disambiguate — the baseline of 4 applies. The description correctly implies no arguments are supplied and that account context comes from the session rather than an input.

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 first clause ('List unpaid invoices in the user's own SingleOps account') is a specific verb+resource, but the very next sentence reveals the tool does not list anything — it returns step-by-step instructions and 'opens nothing by itself'. That reversal leaves the agent with a slightly contradictory picture of whether this tool yields invoice data or a how-to guide. It is anchored to SingleOps and distinguishable from the cotlet_browser_* family, but the framing under the tool's own name is muddled.

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 an explicit two-step workflow: call this to get the procedure, then 'do it with the cotlet_browser_* tools in the user's SingleOps Cloud Browser'. That names the follow-on alternatives and their ordering, which is genuinely useful routing. It stops short of saying when NOT to use it (e.g. when the agent already knows the screens, or when a native API path exists), so it is clear context without exclusions.

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