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

Annotations declare readOnlyHint=true and the description explains why, stating the tool opens nothing by itself and only returns instructional content — this resolves what would otherwise look like a name/annotation conflict. It also discloses what the return content contains (screens, buttons, fields) and why the API path is unavailable (paid add-on). It stops short of covering auth, rate limits, or the cloud-browser session prerequisites.

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 handoff to cotlet_browser_* are front-loaded, but the trailing paragraph about Fiken's REST API pricing (99 NOK/month, Brønnøysundregistrene, a checked-on date) is bulky justification rather than operational guidance. It earns some place by explaining why browser automation is used, but it could be compressed to a clause.

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 tool with no output schema, the description carries the needed burden: it says what comes back (step-by-step screens/buttons/fields) and what must happen next. Missing is any statement of output format boundaries or what happens if the account/app isn't available, which keeps it just short of complete.

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 no parameter meaning for the description to add; baseline for a no-param tool applies. The description correctly implies the "input" is conversational context supplied by the agent rather than schema fields.

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 uses a concrete verb and resource ("Create invoice in the user's own Fiken account") and immediately qualifies the counterintuitive part: the tool returns step-by-step instructions rather than performing the creation. It does not explicitly differentiate itself from siblings such as fiken_send_invoice or fiken_add_contact, so the agent must infer ordering, but the actual behavior is unambiguous.

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: call this first to get screens/buttons/fields, then act with the cotlet_browser_* tools in the user's Fiken Cloud Browser, and explicitly says it "opens nothing by itself." There are no explicit when-not conditions or named sibling alternatives (e.g. when to prefer fiken_send_invoice), but the sequencing guidance is strong.

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