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

Annotations declare readOnlyHint=true and destructiveHint=false, which would otherwise look contradictory next to an "add" tool; the description resolves this head-on by stating it "opens nothing by itself" and returns step-by-step instructions with screens, buttons and fields. It also discloses the external integration reality (no API, webhooks, Zapier, or Google Calendar/QuickBooks sync, dated check), which prevents the agent from attempting an unsupported path. This is meaningful behavior beyond what the annotations encode.

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 behavior and the handoff to browser tools are front-loaded in the first two sentences, which is the right order. The trailing sentence about DusterBook's lack of API/webhooks/Zapier and calendar/accounting sync is useful guardrail context but is dense and only tangentially about this specific action.

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?

For a zero-parameter, no-output-schema tool embedded in a multi-step browser workflow, the description covers what it returns, what it does not do, and what to call next. The remaining gap is what customer information the user must supply, which the agent has to discover from the returned steps.

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 (empty object schema, additionalProperties false), so there is no parameter meaning to add; the baseline for a 0-param tool applies. The description compensates indirectly by explaining that the actual data entry happens later through the cotlet_browser_* tools, though it never says which customer fields will be requested.

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?

Names a specific verb and resource ("Add customer in the user's own DusterBook account") and immediately corrects the expectation by saying it "Returns how to do it in DusterBook step by step (screens, buttons, fields) and opens nothing by itself." The apparent mismatch between the tool name and its actual output is resolved in the same breath, so an agent knows this is a guidance tool, not a mutator. It does not, however, differentiate itself from sibling DusterBook actions like dusterbook_create_invoice or dusterbook_schedule_job.

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?

Gives explicit next-step routing: after getting the steps, "do it with the cotlet_browser_* tools in the user's DusterBook Cloud Browser," which tells the agent exactly which sibling family to chain into. It also pre-empts a wrong path by noting DusterBook has no API. What it lacks is an explicit when-not condition or a statement of what user input is required before calling.

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