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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered; the description adds genuinely non-redundant context: it is free and opens no browser session, so there is no cost/session side effect to calling it speculatively. With no output schema, listing the kinds of content returned (browser choice, sign-in link, method, screens, menus, notes, dedicated tools) is valuable behavioral disclosure. It does not say how large the response is or whether repeated calls are cheap beyond 'free'.

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 purpose and the content inventory come first, followed by the call-timing rule and the coverage/cost caveats, so it is front-loaded and has no filler. The long comma-separated content list in the first sentence is dense and could be trimmed to the items an agent actually needs to plan around. Length is proportionate to a guidance tool with two optional params.

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-param, read-only reference tool with no output schema, the definition covers what it returns, when to call it, what it costs, and how it behaves for unknown apps — enough to invoke it correctly. The remaining gap is invocation cadence and expectation of response size, which matters because the guide is meant to be consumed before a sequence of browser steps.

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% and both parameters (app, task) are already documented in the schema, including the AniList default, so the schema carries the load. The description adds only indirect meaning for 'app' via the note that apps outside the catalog fall back to the general method; it says nothing extra about how the 'task' string shapes the returned guide. Baseline 3 is appropriate.

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 operating guide for Cotlet's Cloud Browser) and enumerates what it returns: which browser to use, the sign-in link, the step-by-step method, screens/menus/actions, notes, and any dedicated tools. That distinguishes it clearly from action siblings like cotlet_browser_click or cotlet_browser_navigate. It stops short of a crisp verb phrase ('how to work' describes the content, not an action), which keeps it off a 5.

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' is an explicit trigger tied to a specific moment in the workflow, which is exactly what an agent needs to sequence it ahead of the browser_* tools. It also scopes coverage ('Works for any web app; one outside Cotlet's catalog gets the general method'), but gives no when-not guidance, such as whether to re-call per session, per app, or skip when dedicated app tools are already known.

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