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 new context beyond that: the tool opens nothing itself, its payload is UI instructions, and the follow-up mutation happens through the browser tools — a useful division of responsibility for an agent planning a multi-step task.

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 core message is front-loaded and useful, but there is filler ('from ChatGPT, Claude or any AI agent') and a trailing sentence about Kustomer's official REST API and read-only MCP server that is tangential and could distract an agent toward a path it cannot invoke. Trimming the last sentence would sharpen the definition considerably.

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 so by stating the response is step-by-step instructions with screens, buttons and fields. Combined with the pointer to the browser tools, an agent has enough to plan the workflow; only failure/prerequisite cases (e.g., not signed in) are unaddressed.

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?

The tool takes zero parameters (schema is an empty object with additionalProperties false), so parameter semantics carry no burden and the baseline is 4. The description adds no param detail, which is appropriate here.

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 specific resource (conversations in the user's own Kustomer account) and then clarifies the actual behavior: it returns step-by-step Kustomer UI instructions rather than performing the search. The opening verb 'Search' slightly oversells what the tool does before the corrective 'Returns how to do it... and opens nothing by itself', but an agent can still tell what it gets.

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?

It gives a clear workable sequence: call this to get screens/buttons/fields, then perform the action with cotlet_browser_* tools in the Kustomer Cloud Browser. It does not explicitly exclude alternatives or distinguish itself from general guidance tools like cotlet_app_guide, so it stops short of full when/when-not guidance.

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