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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds genuinely useful facts: the call is free and does not open a browser session, and it is static guidance rather than live page interaction. It does not describe response shape or size, but the cost/session disclosure is exactly the kind of context annotations cannot express.

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 opening sentence is a long comma-delimited list of outputs that is harder to scan than a short bulleted framing would be. Nothing is strictly wasted, but the payload list crowds out the more actionable instruction ('call before the first browser step'), which arrives late.

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 two optional parameters, no output schema, and rich annotations, the definition covers what an agent needs: the trigger point, the scope (any web app), the fallback for uncataloged apps, and the content of the returned guidance. Only the repeat-call/no-repeat cadence is left 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% and both parameters are documented with descriptions and a stated default (Sunsama), so the baseline is 3. The description implies what the `app` argument steers (which browser, which method, which dedicated tools) but adds no format or slug guidance beyond the schema.

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 pre-flight briefing tool: it returns which browser to use, the sign-in link, the step-by-step method, the app's screens/menus/actions, notes, and any dedicated Cotlet tools. That distinguishes it well from the cotlet_browser_* siblings, which perform actions rather than explain them. The verb is implicit (it is a retrieval/guide tool rather than a stated 'Returns X'), which keeps it just short of a 5.

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" is an explicit trigger condition, and "Works for any web app; one outside Cotlet's catalog gets the general method" covers the edge case of uncataloged apps. What is missing is a counterpart statement (e.g., call it once per app/session, do not repeat before every click), so the agent must infer the boundary with the browser tools.

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