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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant context: the tool opens nothing by itself, and its return value is a screen/button/field walkthrough rather than data. Omitting whether that guidance is cached or dated is a minor gap.

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 critical 'opens nothing by itself' and the browser handoff are present, but the opening clause listing 'ChatGPT, Claude or any AI agent' is marketing padding, and the closing API/integration inventory is verbose for what it contributes. Three meandering sentences when two tight ones would carry the same load.

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, side-effect-free tool with rich annotations and no output schema, the description covers what the agent needs: what it returns (step-by-step guidance), what it does not do (no action, no API behind it), and what to call next. The lack of any note on freshness or reliability of the referenced UI steps is the only real omission.

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 no parameters, so there is no parameter semantics to convey; the schema is empty with additionalProperties=false and coverage is nominally 100%. The description correctly implies the call is argument-free and scoped to the user's own account, adding nothing misleading.

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?

States a specific verb and resource (list unpaid invoices in the user's own Arborgold account) and immediately clarifies that the tool returns step-by-step instructions rather than the invoice data itself, which distinguishes it from a data-fetch tool. The lingering tension between the name 'list_unpaid_invoices' and the actual behavior (returns a how-to guide) costs it a point, but the truth is stated explicitly rather than left to be discovered.

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?

Explicitly routes the agent onward: get the steps here, then execute with the cotlet_browser_* tools against the user's Arborgold Cloud Browser. It also explains why this path exists (no official API, webhooks or Zapier app). No explicit when-not conditions or named sibling alternatives from the arborgold_* family are given, keeping it below the top score.

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