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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds two facts not in annotations: the call is free and opens no browser session, which matters for cost and side-effect reasoning. It does not say the result is unstructured text guidance, but for a read-only lookup tool this is a modest gap rather than a serious one.

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 an overlong run-on built from a comma-separated inventory ('which browser..., the method..., the app's screens, menus and actions, notes, and...'), which is harder to parse than a short purpose statement plus a list. The last two short sentences are efficient and well-placed, but the core sentence should be restructured.

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 burden of explaining what comes back, and it does list the returned content. Combined with the when-to-call rule and the catalog fallback, an agent has enough to invoke it correctly. Missing only the output form (prose vs. structured) for full completeness.

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%: both 'app' (with the Bloomerang default) and 'task' are fully documented in schema. The description adds no guidance on how detailed 'task' should be or what happens when 'app' is omitted, so it does nothing beyond the schema. 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 names the resource (guidance for working in an app via Cotlet's Cloud Browser tools) and enumerates what the guidance covers: browser choice, sign-in link, method, screens, menus, actions, notes, and dedicated tools. It is clearly not one of the cotlet_browser_* action siblings, but it states its purpose as a list of contents rather than a verb ('returns instructions that...'), which leaves the operation slightly implicit.

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 a concrete trigger and ordering relative to the browser_* siblings. It also scopes applicability ('works for any web app; one outside Cotlet's catalog gets the general method'), so the agent knows coverage limits. No explicit when-not-to-use case, but the ordering rule effectively provides one.

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