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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, and the phrase 'opens nothing by itself' reinforces rather than contradicts them. The note that no public API exists and that QuickBooks is the only documented integration adds useful context about why browser automation is required, but the description does not describe the shape of the returned steps.

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 operative instruction is front-loaded and clear, but the trailing API-discovery narrative (404s on /api, /developers, /docs, FAQ naming QuickBooks) is justification rather than guidance an agent needs to call the tool. It is informative but disproportionate to a no-parameter lookup 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?

For a zero-parameter read-only tool with no output schema, the definition covers what is returned (ordered steps with screens, buttons, fields), that nothing is mutated, and which companion tools carry out the change. Only the precise return container/format 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, so there is nothing for the description to disambiguate; the schema is fully closed with additionalProperties=false. Baseline 4 applies.

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 makes clear this tool returns step-by-step instructions for setting up a custom role (screens, buttons, fields) rather than performing the action itself, and that the action is then done via cotlet_browser_* tools. What it does not do is distinguish this 'custom role' from the sibling ez_lawn_biller_staff_role, so the agent must infer which role tool applies.

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 states the workflow clearly — get the steps here, then execute with cotlet_browser_* in the Cloud Browser — which is genuine usage guidance. However, there is no when-not condition and no routing advice against the very similar staff-role sibling, so the agent gets a sequence but not a selection rule.

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