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

The annotations declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with the concrete claim that it 'opens nothing by itself' — valuable confirmation that no state changes on the account. It also discloses the integration constraint (no public API, QuickBooks-only), which explains why browser automation is required. It does not describe the shape or length of the returned instructions.

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 value — returns steps, changes nothing, then use the browser tools — is front-loaded and useful. The trailing sentence about 404s on ezlawnbiller.com/api, /developers and /docs on 11 Nov 2026 is over-detailed provenance that does not help an agent select or invoke the tool. Trimming it would sharpen the definition.

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, no output schema, and read-only annotations, the description carries most of the burden and does so: it explains what is returned conceptually and what to do next. Missing only an indication of how the returned steps are structured or how strictly they should be followed.

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 to disambiguate. The description correctly implies no inputs are needed because the guidance is generic per-task. Baseline 4 applies for a zero-parameter 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 explicitly states the actual behavior: it returns a step-by-step how-to (screens, buttons, fields) rather than performing the creation, which resolves the ambiguity in the 'create_a_draft' name. The resource and domain (EZ Lawn Biller drafts) are concrete. It stops short of a crisp one-line 'this is a guidance tool, not a writer' framing, so an agent must read the second sentence to understand the real purpose.

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 a follow-up path: use the cotlet_browser_* tools in the Cloud Browser to actually perform the steps. However, it never says when to choose this over the many sibling draft tools (apply_draft_to_live, delete_draft, save_notice_draft) or when a direct action would be preferable. Usage is implied rather than contrasted against alternatives.

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