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

The key behavioral fact — 'opens nothing by itself' — is stated plainly and matches the readOnlyHint/idempotentHint annotations, so there is no contradiction. It also discloses the return payload shape (screens, buttons, fields) and the required follow-up tooling. Given annotations already declare the safety profile, this adds genuine context rather than repeating it.

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?

Two sentences, front-loaded with the action and immediately followed by the crucial clarification that nothing is executed. The API sentence has a slight trivia smell (the 'checked 23 Oct 2026' date stamp) but earns its place by explaining why browser automation is the route.

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 guidance tool, the description covers purpose, return content, non-execution guarantee, and next step. An agent has enough to call it correctly and knows not to expect the invoice to be approved afterward.

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 schema imposes no semantics burden and the baseline is 4. The description correctly implies no inputs are needed for the guidance call, consistent with the empty schema.

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 a specific verb+resource (approve invoice in the user's AroFlo account) and explicitly reframes what the tool actually does: returns step-by-step instructions rather than performing the approval. It also points at the cotlet_browser_* tools needed to execute the action, which separates it from genuine action tools. It never names the closely related cotlet_app_guide, so sibling differentiation is only partial.

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?

Usage is spelled out as a two-stage workflow: call this to get the screens/buttons/fields walkthrough, then drive the AroFlo Cloud Browser via cotlet_browser_* tools. The API note explains why the API route is unavailable (off by default, requires support to enable), which effectively excludes an alternative path. What's missing is explicit guidance on when to call cotlet_app_guide instead.

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