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 genuinely non-obvious behavior: 'Free, no browser session' tells the agent this call consumes no browser session or balance (meaningful next to cotlet_balance), and it enumerates the content returned. It does not describe output format or size, but the cost/no-session disclosure is a real value-add beyond the annotations.

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?

Roughly 60 words, front-loaded with the trigger condition ('Call it before the first browser step in an app' is embedded mid-paragraph but the purpose leads). The first sentence is a long run-on enumeration joined by commas and 'and', which costs a little readability. No filler sentences, though.

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 return-value burden and does: browser selection, sign-in link, method, screens/menus/actions, notes, dedicated tools. Combined with the cost/session disclosure and the placement instruction, an agent has everything needed to decide and call it correctly.

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 are documented structurally. The description nonetheless adds edge-case meaning for 'app': any web app works, and an app outside Cotlet's catalog falls back to the general method rather than failing. That tells the agent how to behave with an unmatched value, which the schema's 'name or Cotlet slug' phrasing does not.

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 tool returns 'how to work in an app' guidance for the Cloud Browser — browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and any dedicated app tools. That is specific enough to separate it from the sibling browser action tools (click, fill_form, navigate). It stops short of naming a crisp verb ('Get'/'Return'), and the opening clause is convoluted, so a 4 rather than 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' gives an explicit trigger point relative to the cotlet_browser_* siblings. 'Works for any web app; one outside Cotlet's catalog gets the general method' covers the fallback case. It never states a when-not condition (e.g. skip it on repeat visits within an already-guide-loaded session), so it is context-rich but not airtight.

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