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

The annotations declare readOnlyHint=true and destructiveHint=false, and the description reinforces that behavior with 'opens nothing by itself,' so the safety profile is reinforced rather than merely restated. It adds the critical behavioral fact that the tool returns textual instructions and requires a separate browser step. Returning instructional text rather than acting is a key distinction for an agent planning a task, and the description makes it explicit. Rate limits and permission requirements are not discussed, which keeps it from a 5.

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 is front-loaded and useful, but the definition is padded. 'from ChatGPT, Claude or any AI agent' adds nothing to invocation decisions, and the closing note about Tripleseat's REST API, OpenAPI spec, and lack of an official MCP server is background information that does not help an agent call this tool.

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 annotations that already cover the safety profile, the description still carries the essential information: it returns step-by-step UI instructions, it performs no action, and a separate browser tool sequence is required. What is missing is only minor: nothing about what the returned instructions look like or whether they can be reused across accounts.

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, so the baseline is 4. The description correctly conveys that all inputs are handled in the subsequent browser step, and there is nothing in the schema that the description needs to explain.

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 pairs a specific verb and resource ('Convert lead to event in Tripleseat') and then reveals the actual mechanism: it returns step-by-step instructions rather than performing the conversion. That disclosure is essential because the tool name alone implies a write action, and the description corrects that impression. It stops short of 5 only because the opening phrase ('from ChatGPT, Claude or any AI agent') blurs the purpose rather than sharpening it.

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 clearly lays out the workflow: call this first to get the screens, buttons, and fields, then execute the conversion using cotlet_browser_* tools in the Tripleseat Cloud Browser. No explicit when-not guidance is given, and it doesn't contrast with cotlet_app_guide, which covers similar ground for the Tripleseat app, so the agent has to infer the boundary. Clear context, but the alternatives are unnamed.

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