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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds one genuinely new behavioral fact — 'Free, no browser session' — which tells the agent this does not consume credit or spawn a Cloud Browser instance. Beyond that it does not describe response shape, freshness of the guidance, or whether the method can go stale.

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 instruction ('Call it before the first browser step') is front-loaded, but the opening sentence is a long comma-chained inventory of contents that is harder to parse than needed. The closing facts (any web app, free, no session) do earn their place; the middle list could be trimmed.

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 two-optional-parameter, no-output-schema retrieval tool, the description covers what is returned, when to call it, coverage limits, and cost. It leaves open whether the returned guidance is per-workspace or global and whether calling it repeatedly yields the same content, but nothing essential to invoking it is missing.

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?

Schema coverage is 100%: 'app' is documented as name or Cotlet slug with a stated default of Klook, and 'task' as the user's goal in their words. The description mentions 'which browser to use for this workspace' but never ties that to the app or task parameters, so no meaning is added beyond the schema. Baseline 3 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 states a specific resource — a per-app playbook covering browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and dedicated tools — so an agent knows this returns guidance rather than performing the browser action itself. That contrasts clearly with the cotlet_browser_* siblings, though the framing sentence ('How to work in an app by clicking...') reads more like a topic heading than a verb.

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?

Explicit timing guidance: 'Call it before the first browser step in an app,' plus a coverage note that apps outside the catalog get the general method and that it costs nothing and opens no session. It stops short of stating when to skip it (e.g., re-calling mid-task), but the placement rule is unambiguous.

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