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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the cost model ("Free"), the side-effect profile ("no browser session" is not started), and the degraded-mode behavior for uncatalogued apps. These are exactly the traits an agent cannot read off the annotations and that affect whether it is safe to call this repeatedly before acting.

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 purpose is front-loaded in the opening clause and every subsequent phrase maps to something the guide returns, so there is no filler. The single long sentence with a seven-item list is dense and slightly hard to scan, which is the only thing keeping it off a 5.

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 supplies the trigger condition, the content of the response, the cost, and the fallback path — enough to call it correctly. It does not indicate the shape of the returned guide (structured sections vs. prose) or whether calling it repeatedly with the same app is cheap in tokens, but neither is required for 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% and both parameters carry descriptions including the Property Finder default, so the schema does the heavy lifting and a baseline 3 applies. The description adds only indirect meaning — that the app parameter accepts a Cotlet slug or an unknown app, and that the task should be in the user's own words — without expanding on format or limits.

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 names a concrete retrieval resource and enumerates its payload: workspace browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and app-specific tools. That is specific enough to separate it from the browser_* action siblings, which all perform operations rather than return guidance. It stops short of naming the nearest sibling (cotlet_apps, which lists apps) as the contrasting option, so it is clear but not fully differentiated.

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, and "Works for any web app; one outside Cotlet's catalog gets the general method" covers the fallback case. What is missing is any negative guidance or named alternative (e.g. use cotlet_apps first to find the slug), so the agent still has to infer the ordering with the catalog tool.

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