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 behavior: 'Free, no browser session,' which tells the agent this call has no cost and does not consume a browser tab, plus the note that unknown apps fall back to a general method. Return contents are sketched but not itemized in depth.

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 guidance sentence is front-loaded and the call-timing rule follows, which is good ordering, but the middle is a long comma-chained inventory of return contents that reads as filler. The Planfy action list is useful but appended as one more item in the list rather than set apart. Tightening the contents enumeration would improve it.

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?

There is no output schema, so the description must describe the payload, and it does name the components an agent will receive: browser choice, sign-in link, method, screens/menus/actions, notes, and dedicated tools. Combined with the zero-required-parameter schema and the call-ordering rule, an agent has enough to invoke this correctly; only the shape and size of the returned guide remains unspecified.

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%, with both optional parameters and their defaults (app defaults to Planfy) fully documented. The description adds only the Planfy action list ('Book appointment, Reschedule appointment, Find free slots...'), which hints at what the task parameter can express but does not explain how app/task shape the response. Baseline 3 applies 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 names a specific resource (a per-app operating guide) and enumerates what it returns: which browser to use, the sign-in link, the step-by-step method, screens/menus/actions, notes, and app-specific tools. That enumerations distinguishes it from the cotlet_browser_* action tools. It is slightly diffuse because the contents are delivered as a comma-separated run-on rather than a crisp statement of purpose.

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?

Explicit timing is given: 'Call it before the first browser step in an app,' which is exactly the routing rule an agent needs relative to cotlet_browser_open/navigate/click. It also states coverage ('Works for any web app; one outside Cotlet's catalog gets the general method') and scopes Planfy actions. There is no explicit when-not or named alternative, but the pre-step rule carries most of the guidance burden.

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