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

Annotations already mark this as a safe, idempotent, closed-world read, and the description adds the crucial fact the annotations cannot convey: the call 'opens nothing by itself' and only returns a procedure. The no-API / no-sync note preempts an expected integration path. It leaves out return shape and whether the guidance depends on account state, so it is strong but not complete.

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 constraint — it returns steps and changes nothing — is front-loaded in the first two sentences and the follow-up tool family is named immediately after. The final sentence is functional but wordy, stacking three negations (API, webhooks, Zapier) plus a Google Calendar/QuickBooks claim and a check date, which is more insurance against false assumptions than strictly 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 no output schema and no inputs, the description must carry the whole burden, and it covers what the tool returns, what it does not do, and which tools perform the actual action. The remaining gap is the absence of any statement that the returned steps are fixed/generic (since no job details can be passed in) and any prerequisite about the user's Cloud Browser session.

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 the baseline is 4. The description does not need to explain arguments, and the empty schema is consistent with a fixed-procedure lookup tool. It could have clarified that the returned steps are therefore generic rather than tailored to a specific job.

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 and clarifies the true nature of the tool: it returns step-by-step instructions (screens, buttons, fields) rather than creating anything. That is a meaningful disambiguation from sibling write tools like dusterbook_create_invoice or dusterbook_create_quote. It stops short of 5 because the name/title say 'schedule job' while the tool only yields a generic guide, and the description never states whether the steps are scheduling-specific or generic DusterBook navigation.

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 explicit sequencing: call this first to get the procedure, then execute it with the cotlet_browser_* tools in the user's DusterBook Cloud Browser. It also removes a tempting alternative by stating DusterBook has no API, webhooks, or Zapier app, so an agent will not look for one. No explicit when-not-to-use condition is given (e.g. when the user already knows the flow or when the browser session is absent).

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