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

Annotations already declare readOnlyHint and destructiveHint=false, and the description reinforces rather than contradicts them by stating it 'opens nothing by itself'. It adds genuinely useful context beyond the annotations: the return shape is procedural (screens, buttons, fields) and the follow-up tools are named. It stops short of stating whether the instructions cover all search filters or what happens if the user lacks access.

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 key constraint - it returns instructions and opens nothing - is front-loaded in the first sentence. The closing note on Trengo's REST API and the absence of an official MCP server is relevant rationale for why UI automation is needed, though it is the weakest-earning sentence and could be trimmed.

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 parameters, no output schema and full annotation coverage, the description needs only to explain what comes back and what to do next - both are covered. The remaining gap is sibling positioning: an agent seeing trengo_list_conversations and cotlet_app_guide alongside this cannot tell from the description alone which entry point to use.

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 fully closed (additionalProperties: false), so there is nothing for the description to disambiguate. Baseline for a zero-parameter tool applies, and the description correctly implies no query is passed in by deferring the actual search work to the browser tools.

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 name reads as a data-returning search, but the description explicitly corrects that: it 'Returns how to do it in Trengo step by step (screens, buttons, fields) and opens nothing by itself'. That is a specific and honest statement of what the tool produces. It falls short of 5 because it never distinguishes itself from the close sibling cotlet_app_guide, which plausibly serves the same instructional role.

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 workflow: call this to get the steps, 'then do it with the cotlet_browser_* tools in the user's Trengo Cloud Browser'. However, it offers no exclusion criteria against trengo_list_conversations, trengo_read_a_conversation, or cotlet_app_guide, leaving the agent to guess which of several conversation-related tools to pick.

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