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 two facts the annotations do not carry: the call is free and opens no browser session, which tells the agent there is no side effect or resource consumption. It could say more about output format or size, but the key behavioral traits are present.

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 trigger is front-loaded in the first sentence of the body ('Call it before the first browser step in an app'), and the enumeration of returned content is a single dense sentence rather than padding. The remaining clauses ('Works for any web app', 'Free, no browser session') each carry distinct information. It is slightly list-heavy but every item earns its place.

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?

With no output schema, the description must convey what comes back, and it does so by naming the components of the guidance (browser choice, sign-in link, method, screens, menus, actions, notes, dedicated tools). Both optional parameters are covered by the schema. What is missing is any sense of output shape or length, which is a minor gap for a pure guidance-retrieval tool.

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 the schema already documents both 'app' (name or Cotlet slug, default Bark) and 'task' (user's goal in their words). The description does not elaborate on how the app name is resolved or how the task string influences the returned guidance, so it adds no meaning beyond the structured fields. 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 clear resource — operating guidance for a web app inside Cotlet's Cloud Browser — and enumerates what the result contains (which browser to use, sign-in link, step-by-step method, screens, menus, actions, notes, dedicated tools). It is distinguishable from the cotlet_browser_* siblings, which perform actions rather than explain them. The verb phrase 'how to work in an app' is slightly abstract, which keeps it short of 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' gives an explicit triggering condition with clear ordering relative to the browser tools. It also clarifies the fallback case ('one outside Cotlet's catalog gets the general method'), so the agent knows it always applies. It does not name siblings such as cotlet_apps (catalog listing) or cotlet_whoami as alternatives, so routing is implied rather than demonstrated.

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