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 bar is covered. The description adds two genuinely new behavioral facts: the lookup is free and opens no browser session, which an agent needs in order to decide whether calling it is cheap. It does not describe the shape or length of the returned guidance, which is the remaining gap.

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 opening sentence is a long colon-delimited inventory that is slightly overloaded, but the three short follow-on sentences (when to call, coverage, cost) are well front-loaded and each earns its place. No filler or repetition.

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 correctly takes on the job of enumerating what comes back (browser choice, sign-in link, method, screens/menus/actions, notes, dedicated tools) and sets expectations for uncatalogued apps. For a zero-required-parameter, read-only lookup this is close to complete; only the size/format of the returned guide is unstated.

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 carry their own descriptions, including the 'Quora' default, so the baseline applies. The prose hints that the guide is keyed to the workspace and the app's dedicated tools, but adds no syntax, fallback behavior, or significance for the optional 'task' parameter beyond what the schema states.

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 explicitly frames this as a guidance/knowledge tool that returns the workspace's browser choice, sign-in link, step-by-step method, screen/menu/action maps, notes, and any dedicated app tools. That content list distinguishes it from the cotlet_browser_* action siblings and from cotlet_apps (catalog lookup). The purpose is clear, though the headline phrase 'how to work in an app' is not a verb+resource formulation, 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 explicit timing, and 'Works for any web app; one outside Cotlet's catalog gets the general method' pre-answers the coverage question. It does not explicitly state when-not to call it or point at cotlet_apps as the alternative for discovering apps, so the routing guidance is clear but not exhaustive.

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