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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds two genuinely useful behavioral facts beyond the annotations: the call is 'Free' and involves 'no browser session' — important because the surrounding tools do consume session/credits. It does not say what the response looks like (structured text vs. instructions), though that is partly implied by the content enumeration.

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 purpose and followed by the invocation rule and scope caveat. The long colon-delimited enumeration of guide contents is dense but each item maps to something the caller would want; it could be trimmed slightly without loss.

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, read-only, no-output-schema tool, the description covers what the guide returns, when to call it, and that it works for arbitrary apps. Missing only the shape of the returned content and how it relates to cotlet_apps discovery, which is minor given the tool's simplicity.

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 are documented in-schema, including the 'Privy' default for app and the 'in their words' framing for task, so the baseline is 3. The description adds only marginal meaning beyond that: 'works for any web app' clarifies that app is not restricted to a catalog enum, and unknown apps yield the general method. No format or length guidance is added.

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 the resource (a step-by-step how-to guide for working in a specific web app via Cotlet's Cloud Browser) and enumerates what the guide contains: browser choice, sign-in link, screens, menus, actions, notes, and app-specific tools. It is clearly a guidance/retrieval tool rather than a browser action tool, distinguishing it from the many cotlet_browser_* siblings. The only weakness is that the verb is implicit ('How to work in an app') rather than an explicit 'returns/retrieves', so the agent must infer it is a lookup.

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 gives a direct invocation rule: 'Call it before the first browser step in an app,' which tells the agent exactly where this fits in a sequence ahead of cotlet_browser_open/click. It also covers the fallback case ('one outside Cotlet's catalog gets the general method'). It does not explicitly name sibling tools like cotlet_apps for discovering catalog entries, so routing to the catalog is left to inference.

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