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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with the explicit 'opens nothing by itself' plus a statement of what is returned (step-by-step screens, buttons, fields). That is the exact behavioral fact an agent needs to avoid assuming a write happened. It stops short of stating whether a browser session must already exist before handing off to cotlet_browser_*, which is the remaining operational unknown.

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 are front-loaded and earn their place, but the trailing sentence about Fatture in Cloud's REST API v2, SDI e-invoices and the absence of an official MCP server is irrelevant to calling this tool and reads as boilerplate filler. 'from ChatGPT, Claude or any AI agent' is also padding that adds no decision value.

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?

As a zero-parameter guidance tool with no output schema, the definition covers what an agent needs: it is read-only, it returns procedural steps, and it hands off to cotlet_browser_* for execution. The gap is preconditions, specifically whether a Cloud Browser session must be opened with cotlet_browser_open before following up, which is left unstated.

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. Baseline for a no-param tool with full schema coverage. No parameter detail is missing because no parameters exist.

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 (a client) and the target app (Fatture in Cloud), and crucially clarifies that the tool 'Returns how to do it ... step by step (screens, buttons, fields)' rather than performing the add. That distinguishing detail is specific. It loses a point because the leading sentence 'Add client in the user's own Fatture in Cloud account' reads like a mutation and only the second sentence corrects that impression.

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?

There is clear workflow routing: this tool gives the instructions, then 'do it with the cotlet_browser_* tools in the user's Fatture in Cloud Cloud Browser'. However, no when-not guidance is given and the sibling cotlet_app_guide is never mentioned, so an agent cannot tell which guidance tool to pick. It also never explains why adding a client is a guide-only tool when siblings like fatture_in_cloud_create_invoice act as real API operations, leaving an important selection ambiguity.

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