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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavior fact beyond them: 'Free, no browser session,' meaning invoking it does not open or consume a Cloud Browser session unlike the browser_* siblings. Beyond that it does not describe the shape of what comes back (structured sections vs. prose), which matters for a zero-output-schema tool.

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?

Ordering is sensible: what it returns, then the call trigger, then scope, then a concrete example. The opening sentence is an overstuffed colon-list and the closing Tradify action enumeration ('Create job, Create quote, Send invoice, Schedule staff, List unpaid invoices') is the least load-bearing part, though it does ground the tool in a real example.

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-only guidance tool with no output schema, the description adequately enumerates what the response contains (browser choice, sign-in link, method, screens/menus/actions, notes, dedicated tools), which compensates for the missing output schema. What it omits is how the agent should consume the result, e.g., whether the returned method supersedes generic browser_tool usage or must be followed step by step.

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 parameters (app, task) are already documented, and the description's restatement of the Tradify default and the user-words framing adds little. The one real addition is behavioral semantics for 'app': an app outside Cotlet's catalog yields the general method rather than an error, which the schema does not convey. Baseline 3 is appropriate when the schema does the heavy lifting.

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-retrieval tool, not an action tool: it returns which browser to use, the sign-in link, a step-by-step method, screens/menus/actions, and app-specific tools. It distinguishes itself from the cotlet_browser_* siblings by being the pre-step briefing. The first sentence is a long run-on that buries the verb ('How to work in an app') rather than stating plainly 'returns a playbook.'

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?

Gives an explicit trigger: 'Call it before the first browser step in an app,' which tells the agent both when and (implicitly) that later calls are unnecessary. Adds scope guidance: 'Works for any web app; one outside Cotlet's catalog gets the general method,' so the agent knows unknown apps are still supported. It never names a competing sibling to avoid, so the routing is implied rather than fully stated.

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