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

Annotations already declare readOnly=true, idempotent=true, destructive=false, openWorld=false, so safety and side-effect profile are covered. The description still adds genuinely new context with "Free, no browser session" — telling the agent this consumes no session/credits, which no annotation conveys. Beyond that it does not describe latency, caching, or whether the returned guidance can go stale; solid but not rich.

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 closing prescriptive sentences are tight and front-loaded well enough, but the opening sentence is a long run-on list of coverage items, and the trailing Productboard action enumeration ("Search features, Read feedback, Add feedback, ...") largely restates sibling tool names. Roughly a third of the text duplicates information the agent can already see in the tool catalog.

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?

For a guardrail/guide tool with no output schema, the description correctly spends its words on what comes back (browser choice, sign-in link, method, screens, menus, actions, dedicated tools) and on the cost model. An agent knows what it will receive and when to call it; only the routing-versus-dedicated-tools relationship for Productboard remains implicit.

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 description coverage is 100%, with both params documented including the "Default: Productboard" behavior, so the baseline is 3. The description adds one real piece of semantics — that an app outside the catalog falls back to the general method — but does not explain how the `task` parameter shapes the returned guidance beyond what the schema already says.

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 states a specific resource — an in-app working guide for the Cloud Browser — and enumerates its contents (browser choice, sign-in link, step-by-step method, screens, menus, actions, notes, dedicated tools). It separates itself from the raw cotlet_browser_* primitives by framing itself as the thing to consult before clicking. It stops short of a crisp one-line category label, but the resource and intent are unmistakable.

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, actionable trigger, and "Works for any web app; one outside Cotlet's catalog gets the general method" tells the agent how uncovered apps are handled. What is missing is a direct steering statement that for Productboard the productboard_* tools should be preferred over browser clicking — the action list only implies that routing.

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