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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description only needs to add context — and it does, with 'Free, no browser session', which tells the agent there is no cost and that no Cloud Browser session is opened by this call. It also previews the guide's contents so the agent knows what comes back. Slight tension exists between 'Works for any web app' and openWorldHint=false, but that reads as a closed knowledge base with generic fallback, not a real contradiction.

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?

Front-loaded with the purpose, and every clause carries information — there is no filler or restated title. The one weakness is the single long colon-and-comma enumeration ('which browser to use for this workspace and the sign-in link, the method step by step, ...') which is harder to scan than a short bulleted list would be.

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 tool with no output schema, the description covers what is needed: what the guide contains, when to call it, that it is free and session-free, and how unknown apps are handled. Minor gaps remain around caching/repeat calls and guide size, but nothing that would block a correct invocation.

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%, so both `app` and `task` are already documented, making 3 the baseline. The description adds one genuine semantic point beyond the schema: an app outside Cotlet's catalog still returns a usable general method, so the agent knows an unknown `app` value is not a failure case. It does not add anything about how `task` shapes the returned guide.

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 concretely what the tool returns: workspace browser choice, sign-in link, a step-by-step method, the app's screens/menus/actions, notes, and any dedicated app tools. That is far more specific than the title alone and clearly positions it as a guide rather than an action. It does not name a sibling (e.g. cotlet_apps or the browser_* tools) explicitly, so differentiation is implied by 'call it before the first browser step' rather than stated.

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 a concrete trigger point that separates this from the browser action tools. 'Works for any web app; one outside Cotlet's catalog gets the general method' defines scope, including the fallback case. Missing: guidance on whether to call again for a second app or later steps, and any explicit when-not-to-use case.

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