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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds two facts not in the structured fields: 'Free' and 'no browser session'. The session-cost disclosure matters because the sibling browser tools presumably do consume a session, making this a meaningful behavioral distinction. It does not describe response size or format, which keeps it from a 5.

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 content is front-loaded in the first sentence, followed by the trigger condition and the scope caveat, each in one short sentence. The lead sentence is overloaded with a long comma-separated list of deliverables, but every item carries information an agent would use. Minor slack only, such as the vague standalone item 'notes'.

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?

There is no output schema, so the description must carry the return-value burden, and it does by enumerating what the guide contains and noting the fallback for apps outside the catalog. It also tells the agent the call is free and opens no session, which is the key cost consideration before a multi-step browser workflow. What is missing is any hint of guide length or how to apply it to the 'task' parameter.

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 description coverage is 100%, with both 'app' (name or Cotlet slug, default Meevo) and 'task' fully documented in the schema, so the baseline of 3 applies. The description adds only indirect context — that the guide is tailored per app and presumably per task — without explaining how 'task' shapes the returned method. Nothing is misleading, but little is added beyond the 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 states concretely what the tool returns: which browser to use for the workspace, the sign-in link, a step-by-step method, the app's screens/menus/actions, notes, and any app-specific dedicated tools. That is enough to distinguish it from the cotlet_browser_* action siblings, which perform the clicks rather than explain them. The opening phrase is dense and the resource is abstract ('a guide'), but the enumerated contents remove real ambiguity.

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?

'Call it before the first browser step in an app' gives an explicit trigger point in the workflow, which is exactly the routing decision an agent needs against the many cotlet_browser_* siblings. It also states coverage ('works for any web app; one outside Cotlet's catalog gets the general method'), so the agent knows a missing catalog entry is not a failure. No explicit when-not or named alternative is given, keeping it short of a 5.

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