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 genuinely non-structured context: the call costs nothing and opens no browser session, and off-catalog apps still return a generic method rather than an error. It does not describe the shape or length of the returned guidance, which would help an agent plan around it.

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?

It is front-loaded with the trigger ('Call it before the first browser step'), which is good, but the first sentence is a long comma-chained list of what the guide contains that is hard to parse on a single read. Trimming that enumeration into a short payload summary would make the same information land faster.

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 does the work of explaining what comes back: browser choice, sign-in link, method steps, screens and menus, notes, and dedicated tool names. Combined with the cost and coverage notes, an agent has enough to decide to call it and to use the result. It stops short of saying how the returned guidance should be sequenced into subsequent browser calls.

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 description coverage is 100% and both parameters are documented in the schema, including the 'Default: Mautic' behavior and the intent of 'task'. The description adds no meaning beyond that — it never says how the task string steers the returned guidance or what happens when app is omitted. Baseline 3 applies when the schema carries the semantics.

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 enumerates the concrete payload of the guide: which browser to use for the workspace, the sign-in link, the step-by-step method, the app's screens/menus/actions, notes, and dedicated tools. An agent can tell this is a knowledge/instruction retrieval tool distinct from the cotlet_browser_* action tools. It loses a point because the opening clause 'How to work in an app...' describes the content rather than the retrieval action, and no sibling such as cotlet_apps is named for contrast.

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 precise trigger point, and 'Works for any web app; one outside Cotlet's catalog gets the general method' bounds the coverage so an agent knows a miss is not a failure. 'Free, no browser session' tells the agent the call is cheap and safe to make preemptively. What is missing is explicit routing against alternatives such as cotlet_apps for discovering slugs or cotlet_whoami for account context.

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