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 useful non-structured context: it is free, it consumes no browser session, and it degrades to a general method for apps outside Cotlet's catalog — details an agent cannot infer from the hints.

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?

Two sentences, both front-loaded with the important information: what you get first, then when to call it and how it behaves for uncatalogued apps. No filler or restatement of the name/title beyond necessary framing.

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 does the work of describing the return payload (browser/sign-in link, step-by-step method, app screens and actions, notes, dedicated tools) and confirms no browser session is needed. Only minor gaps remain, such as what shape that guidance arrives in or whether it is app-version sensitive.

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 app and task are already documented in the schema, including the Procore default. The description only says the tool works 'in an app' and adds nothing about how the task argument shapes the returned method, so the baseline 3 applies.

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 guidance/knowledge tool that returns the method for operating a specific web app in the Cloud Browser, and enumerates what the guidance contains (browser choice, sign-in link, step-by-step method, screens/menus/actions, dedicated tools). It is distinguishable from the many cotlet_browser_* action siblings because it explicitly frames itself as the thing to consult before those actions, though the phrasing is a comma-heavy list rather than a single crisp verb+resource statement.

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?

Gives a concrete trigger: 'Call it before the first browser step in an app', which directly orders it against the cotlet_browser_* siblings. It also scopes coverage ('Works for any web app; one outside Cotlet's catalog gets the general method'), but never states a when-not condition or names an alternative to use instead.

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