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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: the tool returns procedural instructions rather than performing the merge, and nothing is opened or changed on the user's side. The closing note that Kustomer's official API/MCP server is read-only explains why browser automation is required, though its dated 'checked 17 Oct 2026' aside is peripheral.

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 critical fact — that this returns instructions and performs no action — is buried in the second sentence behind a misleading imperative opening. The final sentence about Kustomer's REST API and official MCP server is tangential to invoking this tool and dilutes the message. Trimming that sentence and leading with 'Returns step-by-step instructions for merging conversations' would be much stronger.

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 zero parameters, no output schema, and rich annotations, the description covers what an agent needs: what it returns (screens, buttons, fields), that it has no side effects, and which tools to use afterward. It does not describe the shape of the returned guide (length, format), but that is a minor gap for a tool this simple.

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 and the schema is empty with additionalProperties=false, so there is nothing for the description to disambiguate. The baseline for a no-parameter tool applies, and the description correctly implies the tool is parameterless by describing no inputs.

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 eventually makes clear that this is a guidance tool, not an action tool: it 'Returns how to do it in Kustomer step by step (screens, buttons, fields) and opens nothing by itself.' However, the opening sentence 'Merge conversations in the user's own Kustomer account' states a verb the tool does not perform, so the real purpose is only established on the second read. It does name the cotlet_browser_* siblings it must be paired with, which helps separate it from the kustomer_* action tools.

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?

The description gives a clear workflow: call this first to get the steps, then execute them with the cotlet_browser_* tools in the Kustomer Cloud Browser. That is a concrete when-to-use and how-to-follow-up instruction. It stops short of stating when not to use it, e.g. whether any sibling can merge directly without browser automation.

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