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

Annotations already declare readOnlyHint=true and destructiveHint=false, but for a tool literally named 'create_estimate' that would be confusing on its own; the description resolves it by stating it 'opens nothing by itself' and only returns instructions. It also explains why the browser path exists (Open API is Pro-only, no official MCP server), which is useful motive but not required to invoke the tool. It could have gone further on prerequisites, cost, or whether the returned steps are account-specific.

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 description is short and mostly earns its words, but the ordering is poor: the load-bearing clarification ('opens nothing by itself') arrives after a sentence that implies creation, so an agent skimming may misclassify it. The final sentence about the Open API and Pro plan is contextual trivia that does not change how the tool is called, and it sits after the actionable content rather than being cut or subordinated.

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 and no output schema, the description must carry the return-value burden, and it does: it says the result is step-by-step guidance covering screens, buttons and fields. The follow-on action is also spelled out. The remaining gap is invocation prerequisites, such as whether the Service Fusion browser session must already exist before this is called.

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 coverage is 100%, so there is no parameter meaning to add. Baseline for a no-parameter tool applies.

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 resource (Service Fusion estimates) and, crucially, discloses that the tool returns a step-by-step how-to rather than creating anything. That distinguishes it from the cotlet_browser_* action tools and from service_fusion_create_invoice/create_job. It loses a point because the opening sentence ('Create estimate in the user's own Service Fusion account') frames the tool as a write operation that the very next clause reverses, forcing the agent to read two sentences to learn what it actually does.

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 an explicit two-step workflow: call this to get the procedure, then execute it with the cotlet_browser_* tools in the user's Service Fusion Cloud Browser. That is real routing guidance an agent can act on. It stops short of 5 because it never states when NOT to use it (e.g. versus cotlet_app_guide) and does not mention prerequisites such as whether a browser session must already be open.

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