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

Annotations already establish readOnlyHint, idempotentHint and non-destructive behavior, so the remaining burden is low. The description still adds real value by stating it 'opens nothing by itself' and that its output is step-by-step UI directions, which an agent needs in order to know it must follow up with browser tools. The official-API/no-MCP-server remark is informational rather than behavioral.

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 two clauses (returns step-by-step guidance, then use cotlet_browser_*) are front-loaded and useful, but the sentence is padded with caller-name branding ('from ChatGPT, Claude or any AI agent') and a dated API/MCP-server aside that does not help an agent decide or call correctly.

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 it does so at a coarse level: step-by-step screens, buttons and fields. Combined with the explicit handoff to the browser tools and the read-only annotation profile, an agent has enough to invoke and follow up correctly.

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 there is nothing for the description to disambiguate and the baseline is 4. No parameter claims conflict with the empty object schema.

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 makes clear this is a how-to/guidance tool, not a mutation: it 'Returns how to do it in Freshsales step by step (screens, buttons, fields) and opens nothing by itself.' That distinguishes it from the cotlet_browser_* siblings it hands off to. It is slightly muddied by phrasing the purpose as the user's action ('Mark deal won or lost in the user's own Freshsales account from ChatGPT, Claude or any AI agent') to the agent that is itself the caller.

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 next step: call this first, then perform the action with cotlet_browser_* tools in the user's Freshsales Cloud Browser. However, it offers no guidance on choosing between this and the related deal-stage sibling (freshsales_move_deal_to_another_stage), which an agent would plausibly confuse with marking a deal won/lost.

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