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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds genuinely useful behavior: it states it is 'Free, no browser session' and enumerates the contents of the returned guidance, which matters because there is no output schema. However, it does not say how large the guidance is, whether it varies per app, or whether it must be called once per app or once per session.

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 is front-loaded and the total length is modest, with no filler sentences. The inventory of return contents is a long comma list inside a single sentence, which is slightly dense but still easy to scan.

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 carries the burden of describing what comes back, and it does so item by item. Combined with the call-timing rule and the catalog fallback, an agent has enough to invoke it correctly. Minor gaps remain around call frequency and whether the returned instructions should be re-fetched between 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 are already documented there, including the Minuba default. The description only reinforces the app scope ('works for any web app; one outside Cotlet's catalog gets the general method') and implies task is free-text user intent. It adds little semantic meaning beyond the schema, so the 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 makes clear this is a guidance/instructions tool for working inside a web app via Cotlet's browser tools, and lists what it returns (browser choice, sign-in link, step method, screens/menus/actions, notes, dedicated app tools). It is distinguishable from the cotlet_browser_* primitives and the minuba_* action tools. The opening phrasing ('How to work in an app') restates the title rather than leading with a crisp verb, which keeps it from 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?

It gives an explicit trigger: 'Call it before the first browser step in an app.' It also scopes coverage: any web app works, and one outside Cotlet's catalog gets the general method, while Minuba gets specific actions. What is missing is an explicit exclusion (e.g., don't call it again for subsequent steps, or when a dedicated minuba_* tool already covers the action).

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