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

The annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new operational context — "Free, no browser session" — which matters for an agent tracking session state and cost. Beyond that it lists the kinds of content returned but says nothing about output shape, length, or how to handle a guide that lacks the needed action.

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 guidance (when to call, what it returns) is front-loaded and useful, but the first sentence is an overly long chain of clauses. The trailing OpenTable action list largely restates the sibling opentable_* tool names, which is redundant for an agent that can already see them.

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-param, read-only, no-output-schema guide tool, the description covers what it is for, when to call it, what it returns, and that it costs nothing and needs no browser session. The main omission is handling when the returned guide does not cover the user's task, but the tool is otherwise correctly scoped.

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%: both `app` and `task` are fully documented in the schema, including the OpenTable default and the 500-character limit. The description mentions "this workspace" and the app's dedicated tools but adds no syntax or usage detail beyond the schema. 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 specific resource (step-by-step guidance for working in a web app through Cotlet's browser tools) and enumerates its contents: browser choice, sign-in link, method, screens/menus/actions, notes, and dedicated tools. It is clearly a pre-flight knowledge lookup rather than a browser action, which separates it from the cotlet_browser_* siblings. It loses a point only because the headline sentence is a long run-on that takes effort to parse.

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 ordering guidance relative to the browser tools, and the note that any web app works while off-catalog apps get the general method covers the fallback case. It does not name a specific alternative tool or state when to skip it entirely, which keeps it short of a 5.

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