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 'opens nothing by itself', which pre-empts the natural assumption that a 'create' tool mutates data. It adds useful return-shape context (step-by-step screens/buttons/fields) beyond the annotations. The trailing 'ERPNext's official API: Yes.' is opaque and adds little.

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?

It is a single dense sentence and the key non-obvious fact (it returns instructions, opens nothing) is placed in the middle rather than front-loaded. Phrases like 'from ChatGPT, Claude or any AI agent' and the fragment 'ERPNext's official API: Yes.' consume space without informing tool selection.

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 critical missing piece would be what the call returns, and the description covers that. The only gap is the absence of any prerequisite or account-state context for a tool that presumes an existing ERPNext account.

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; baseline 4 applies. The description does not misleadingly imply inputs that the schema lacks.

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 states concretely that the tool returns a step-by-step guide (screens, buttons, fields) rather than performing the creation, which resolves the mismatch implied by the name 'create_sales_invoice'. It also names the follow-on tool family (cotlet_browser_*) that actually performs the work. It does not differentiate from the other erpnext_* siblings, which keeps it short of a 5.

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?

A clear two-step workflow is given: call this to get the instructions, then execute them with the cotlet_browser_* tools. There is no explicit when-not-to-use guidance or mention of prerequisites (e.g., needing a connected ERPNext account), but the operative context is unambiguous.

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