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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld=false, so the safety profile is covered. The description adds two things annotations cannot convey: it is free and consumes no browser session, and results degrade to a general method for apps outside the catalog. It does not describe output shape or size, but with no output schema that is a minor omission rather than a serious 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?

Four sentences, front-loaded with the core purpose and ending with the call-timing rule, which is the highest-value instruction. The middle sentence is a long comma-separated inventory that reads as a run-on, but every item in it is information the agent needs about what the tool returns.

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 carries the burden of telling the agent what comes back, and it does so by listing the returned components. It also covers the fallback behavior for uncatalogued apps and the cost profile. What is missing is any indication of response size or whether the guidance is per-app cached, which is minor for a read-only reference tool.

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 carry their own descriptions plus a stated default (DonorPerfect), so the schema does the heavy lifting. The description only gestures at what the parameters influence ('which browser to use for this workspace', 'the app's dedicated tools when Cotlet has them') without explaining how app/task shape the returned guidance. Baseline 3 is appropriate.

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 exactly what the tool returns: browser choice for the workspace, sign-in link, step-by-step method, screens/menus/actions, notes, and any app-specific dedicated tools. That is far more specific than the title and lets an agent distinguish it from the cotlet_browser_* action tools, which it explicitly frames as the downstream consumers. The only weakness is that the headline is a noun phrase ('How to work in an app') rather than a verb naming the retrieval action.

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 an explicit trigger point in the workflow. The coverage statement ('Works for any web app; one outside Cotlet's catalog gets the general method') tells the agent not to worry about catalog membership. It stops short of naming a sibling alternative or an explicit when-not-to-call condition, so it is strong context rather than full routing guidance.

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